SlideShare uma empresa Scribd logo
1 de 4
Baixar para ler offline
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2109
Voice based Gender Recognition
Remna R. Nair1, Bhagya Vijayan2
1Master of Computer Applications, College of Engineering, Trivandrum, Kerala, India
2Asst.Professor, Master of Computer Applications, College of Engineering, Trivandrum, Kerala, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - An Is a human’s voice “UNIQUE”? This is actually
a good question with which most of us are really confused.
Yes!! How much a fingerprint is unique that much a human’s
voice is also unique. Because of thisuniquenessofthevoice, the
human voice can be used for many recognition processes. One
of the most heard recognition processes is “gender”. Itiseasier
for an individual to recognize or identify a human gender by
hearing the voice. So this paper is developed with a mindset to
make the machine learn and identify the gender of the given
voice(real-world input).
Key Words: Decision Trees, Gradient Tree Boosting, Gender
Recognition,Randomforests,SupportVectorMachine(SVM).
1. INTRODUCTION
One of the most common means of communication in the
world is through voice. In the real world, it is possible for a
person to verify the gender of a person through voice. Voice
is filled with lots of linguistic features. These voice features
are considered as the voice prints to recognize the gender of
a speaker. The recorded voice is considered as the input to
the system, which then the system process to get voice
features. Examine the input and compare it with the trained
model, carry out calculations based on the algorithm used
and gives the latest matching output.Genderrecognitioncan
be used along with various other applications. Some are:
 For detecting feeling like male sad, female anger,
etc.
 Differentiating audios and videos using tags.
 Spontaneous salutations.
 Helping personal assistants to answer questions
with gender-specific results etc.
2. METHODOLOGY
The dataset used for detecting gender from the audio files is
retrieved from VoxForge, which is a free speech corpus and
acoustic model repository foropen source speech engines. It
is a large-scale collection of voices of both genders. From the
collected audio files the powerful discriminatingfeaturesare
extracted with which a CSV file is created. With this CSV file
various models are trained using Support Vector Machine,
Decision Trees, Gradient Tree Boosting, Random forests,and
accuracy is calculated. The goal is to compare outputs of
various models and suggest the best model that can be used
for gender recognition by voice in real-world inputs.
In short, the following are the steps followed -
 First, the voice(.wav files) needs to be convertedtoa
form that the system can understand.
 Preprocessing needs to be done on the file to avoid
external noises.
 After the noises have been removed the feature
extraction process can be carried out. It is much
necessary to find out the acoustic features that have
a high discriminative power to classify the genders.
 Next step, is to train the machine with collected
features from the dataset to make the machine
capable to classify the genders of the voice. Here the
machines are trained with four algorithms Support
Vector Machine, Decision tree, Gradient Tree
Boosting, and Random Forest.
 Calculate the accuracy of each algorithm with the
dataset.
 After finding out the best algorithm over the dataset
(based on the accuracy), a particular algorithm will
be used to find out the gender of therealworldinput
given while testing.
Fig -1: Overall process of the system
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2110
3. IMPLEMENTATION
3.1 Data Collection and Preprocessing
For Voice Based Gender Recognition system, the dataset
collected consist of 62,440 audio samples compressed (.tgz)
in sets of 10 files that can be automatically downloaded from
the url
http://www.repository.voxforge1.org/downloads/SpeechCo
rpus/Trunk/Audio/Main/16kHz_16bit. Next step is to
uncompress the compressed files. After uncompressing the
.wav files are obtained. These .wav files are not understood
by the machines, so it needs to be converted into the
machine-understandable format. First, the contents of every
wave file are read, then the features are extracted and saved
into a pandas data frame. In addition to the wave file, the
README files(available with the downloaded dataset) are
also parsed to extract metadata: gender, age range, and
pronunciation. Notably, the python package Scipywavefileis
used to get the audio data, Scipy stats to extract the main
features and Numpy and its fast fourier transform fft and
fftfreq to deduce the .wav data to frequencies.
The data from the .wav files are recorded as amplitude in the
time domain, but the potentially valuable features (with a
higher discriminative power male/female) are frequencies.
To convert the data to frequencies we use DFT (Discrete
Fourier Transforms), particularly the FFT implementation
(Fast Fourier Transform) of the algorithm. The Fourier
transform takes a signal in the time domain (set of
measurements over time) and turns it into a spectrum - a set
of frequencies with corresponding (complex) values. The
spectrum does not contain any information about time!
So, to find both the frequencies and the time at which they
were recorded, the audio signal is splitted into small,
overlapping slices, and the Fourier transform is applied to
each (short time Fourier transform).np.fft.fft returns a
complex spectrum. np.fft.fftfreq returns the sample
frequencies. A sample folder consists of 10 audio recordings
from one particular user. Every .wav file in the folder is
processed in a way that the dominating frequenciesinsliding
windows of 200ms (1/5thofasecond)areextracted.Ifa.wav
file is 4 seconds long, a list containing 20 frequencies will be
extracted. The list of frequencies is then filtered to contain
only values in the human voice range (20Hz < frequency <
280Hz) In addition, values around 50Hzaremostlikelynoise
and also filtered
(https://en.wikipedia.org/wiki/Mains_hum).
3.2 Feature Extraction
The most important featureextracted is the frequencieswith
which more powerful detection can be done. The rest of the
feature depends on these frequencies. Here, the dominating
frequencies are extracted in sliding windows of 200ms.After
the dominating frequencies are extracted other properties
such as skew, kurtosis, etc are calculated. With the following
features a CSV file is created to train the models.
 Mean - Mean specifies the average of all the
dominating frequencies.
 Median - Median is the middle value in the list of
frequencies.
 Mode - Here, mode refers to the frequency that
occurs most often.
 Standard Deviation - By calculating the standard
deviation we could get how much the values in the
dominating frequency list varies from the mean
value of the list.
 Skewness - Skewness shows the asymmetry of the
voice frequencyspectrumaroundthesamplemeans.
If skewness is positive, the spectrum spreads out
more to the right of the mean than to the left side,
and vice versa.
 Kurtosis - Kurtosis shows how muchoutlier-pronea
distributionis.Thefrequencyspectrumwillexhibita
normal shape if kurtosis value is 3.Otherwise if the
value is less than 3, the frequency spectrum will
have fewer items at the center and the tails than the
normal curve but with more items in the shoulders.
If the frequency spectrum is having more itemsnear
the center and at the tails, and few items in the
shoulders compared to a normal distribution with
the samemean and variance, then thekurtosisvalue
is greater than 3.
 Low and High - Low points out the minimum
frequency in the dominating frequency list and high
shows the maximum frequency in the dominating
frequency list.
 First Quartile(Q25 ) - Q25 is the median of the
lower half of the dominating frequency list.Itmeans
that about 25% of the frequency values in the
dominating frequency list liebelow Q25 and 75% of
dominating frequency values larger than Q25.
 Third Quartile(Q75 ) - Q75 is the median of the
upper half of the dominating frequency list. It
suggests that about 75% of the frequency values in
the dominating frequencylistliebelowQ75andonly
25% of dominating frequency values lie above Q75.
 Interquartile Range(IQR ) - IQR means the
frequency ranging between Q25 and Q75 and the
value is the difference between Q75 and Q25 of an
audio.
3.3 Modeling Using Different Machine Learning
Algorithms
The different ML algorithms used are:
Support Vector Machine(SVM) - SVM is a discriminative
classifier that classifies the dataset into two parts of a
hyperplane based on theextractedfeatures.Whenanewdata
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2111
occurs, SVM compares with the existing groups, and with
which greater similarity is found it will be binded with that
particular group.
Decision Trees (DTs) - DTs non-parametric supervised
learning method used for classification and regression. The
goal is to create a model that predicts the gender by learning
simple decision rules inferred from the data features.
Gradient Tree Boosting or Gradient Boosted
RegressionTrees( GBRT) - Gradient Boosting is a
generalization of boosting to arbitrary differentiable loss
functions.
Random Forest - Random Forest is a supervised
classification algorithm. As of the name suggests, this
algorithm creates the forest with a number of trees. In
Random Forest classifier as the number of the tree increases,
the forest gives the high accuracy results.
After modeling with these datasets the best algorithm for
voice-based gender recognition is identified. With the best
model, the real world inputs gender can be identified.
3.4 Testing The Models
For testing the models an interface needs to be created for
recording human voice. After the human voice has been
recorded the noises are cleared out. Then thisrecordedinput
is given to the best model(model with high accuracy
compared to others) and the gender is detected.
4. RESULT
The result is the calculated accuracies from all models. The
accuracies with the different models are compared and the
best model is the one which has thehighestaccuracywiththe
data. The aim of using multiple models is to identify the best
gender recognition model,whichcanbehelpfulindeveloping
future applications. The table below shows the obtained
accuracies of different models.
Table -1: Accuracy Table
Algorithm Used Training Testing
Decision Tree 1.000 0.869
Gradient Boosting 0.958 0.937
Random Forests 0.987 0.893
Support Vector
Machine
0.940 0.905
The result points out that the algorithm with the highest
accuracy is Random Forest. So the best algorithm for Voice
Based Gender Classification is Random Forest.
Assessment of the variable importance - Methods that use
ensembles of decision trees (Tree, Forest, and Gradient
Boosting) can compute the relative importance of each
attribute. These importance values can be used to inform a
feature selection process.
The feature importance depends on how well a feature
discriminates between theclasses.Thestd,devseemstobein
the top 3 most important features in the three tree-based
models.
Chart -1: Decision tree classifier
Chart -2: Gradient Boosting Classifier
Chart -3: Random Forest Classifier
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2112
5. CONCLUSIONS
The aim of this paper is to build a gender recognition
system based on voice. As stated above std, dev, kurtosis,
and skewness seem to have the most discriminant power.
Some unexpected behavior is in the peaks at very low
frequencies (< 50 Hz) that can be viewed in mode and
median. This can be due to the presence of noise in theaudio
recordings. Even if it was filtered, not all sources of noise
were accounted for and furtheranalysisinthiswaywould be
interesting but falls beyond the scope of this project.
Further exploration of potentiallyinterestingfeaturescould
also be pictured out. Other features that were not used here
but could also have good differentiating power are: spectral
flatness spectral entropy, fundamental frequency
At the same time, the set of selected features seem to be
enough for the tested models to achieve good accuracy. The
Random Forest gave the best accuracy followed by the
GradientBoosting, SVM and Decision Tree.
As for the applicability of the tested models, the analysis of
this dataset was supervised and one might not always have
access to the labels of the different categories.Buttheycould
be of great utility in a variety of situations, like discerning
music/speech or a correctly functioning
machine/instrument from a faulty one.
REFERENCES
[1] H. Harb and L. Chen, “Voice-based gender identification
in multimedia applications,” Journal of Intelligent
Information Systems, vol.24,no.2-3,pp.179–198,2005.
[Online]. Available: http://dx.doi.org/10.1007/s10844-
005-0322-8.
[2] Kunyu Chen, Gender Identification By Voice, Stanford
University kunyu@stanford.edu.
[3] T. Vogt and E. André, “Improving automatic emotion
recognition from speech via gender differentiation,” in
Proc. Language Resources and Evaluation Conference
(LREC 2006), Genoa. Citeseer, 2006.

Mais conteúdo relacionado

Mais procurados

Frequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement TechniquesFrequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement TechniquesDiwaker Pant
 
Features image processing and Extaction
Features image processing and ExtactionFeatures image processing and Extaction
Features image processing and ExtactionAli A Jalil
 
Lpc2148 user peripherals
Lpc2148 user peripheralsLpc2148 user peripherals
Lpc2148 user peripheralsfivesquare
 
Lecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard TransformLecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard TransformVARUN KUMAR
 
Gender and Age Detection using OpenCV.pptx
Gender and Age Detection using OpenCV.pptxGender and Age Detection using OpenCV.pptx
Gender and Age Detection using OpenCV.pptxSakshiVishwakarma12
 
Chapter 9 morphological image processing
Chapter 9   morphological image processingChapter 9   morphological image processing
Chapter 9 morphological image processingAhmed Daoud
 
Fundamental steps in image processing
Fundamental steps in image processingFundamental steps in image processing
Fundamental steps in image processingPremaPRC211300301103
 
Watershed Segmentation Image Processing
Watershed Segmentation Image ProcessingWatershed Segmentation Image Processing
Watershed Segmentation Image ProcessingArshad Hussain
 
Frequency Domain FIltering.pdf
Frequency Domain FIltering.pdfFrequency Domain FIltering.pdf
Frequency Domain FIltering.pdfMuhammad_Ilham_21
 
EC8562 DSP Viva Questions
EC8562 DSP Viva Questions EC8562 DSP Viva Questions
EC8562 DSP Viva Questions ssuser2797e4
 
Amplitude Modulation.ppt
Amplitude Modulation.pptAmplitude Modulation.ppt
Amplitude Modulation.pptAbyThomas54
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksstellajoseph
 
Embedded firmware
Embedded firmwareEmbedded firmware
Embedded firmwareJoel P
 
Introduction to image contrast and enhancement method
Introduction to image contrast and enhancement methodIntroduction to image contrast and enhancement method
Introduction to image contrast and enhancement methodAbhishekvb
 

Mais procurados (20)

Image Quantization
Image QuantizationImage Quantization
Image Quantization
 
Frequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement TechniquesFrequency Domain Image Enhancement Techniques
Frequency Domain Image Enhancement Techniques
 
Features image processing and Extaction
Features image processing and ExtactionFeatures image processing and Extaction
Features image processing and Extaction
 
Bit plane coding
Bit plane codingBit plane coding
Bit plane coding
 
Gaussian noise
Gaussian noiseGaussian noise
Gaussian noise
 
Lpc2148 user peripherals
Lpc2148 user peripheralsLpc2148 user peripherals
Lpc2148 user peripherals
 
Lecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard TransformLecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard Transform
 
Image transforms
Image transformsImage transforms
Image transforms
 
Region based segmentation
Region based segmentationRegion based segmentation
Region based segmentation
 
Gender and Age Detection using OpenCV.pptx
Gender and Age Detection using OpenCV.pptxGender and Age Detection using OpenCV.pptx
Gender and Age Detection using OpenCV.pptx
 
Chapter 9 morphological image processing
Chapter 9   morphological image processingChapter 9   morphological image processing
Chapter 9 morphological image processing
 
Fundamental steps in image processing
Fundamental steps in image processingFundamental steps in image processing
Fundamental steps in image processing
 
Adaptive equalization
Adaptive equalizationAdaptive equalization
Adaptive equalization
 
Watershed Segmentation Image Processing
Watershed Segmentation Image ProcessingWatershed Segmentation Image Processing
Watershed Segmentation Image Processing
 
Frequency Domain FIltering.pdf
Frequency Domain FIltering.pdfFrequency Domain FIltering.pdf
Frequency Domain FIltering.pdf
 
EC8562 DSP Viva Questions
EC8562 DSP Viva Questions EC8562 DSP Viva Questions
EC8562 DSP Viva Questions
 
Amplitude Modulation.ppt
Amplitude Modulation.pptAmplitude Modulation.ppt
Amplitude Modulation.ppt
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Embedded firmware
Embedded firmwareEmbedded firmware
Embedded firmware
 
Introduction to image contrast and enhancement method
Introduction to image contrast and enhancement methodIntroduction to image contrast and enhancement method
Introduction to image contrast and enhancement method
 

Semelhante a VOICE-GENDER

Robust Speech Recognition Technique using Mat lab
Robust Speech Recognition Technique using Mat labRobust Speech Recognition Technique using Mat lab
Robust Speech Recognition Technique using Mat labIRJET Journal
 
IRJET- Musical Instrument Recognition using CNN and SVM
IRJET-  	  Musical Instrument Recognition using CNN and SVMIRJET-  	  Musical Instrument Recognition using CNN and SVM
IRJET- Musical Instrument Recognition using CNN and SVMIRJET Journal
 
IRJET- Hearing Loss Detection through Audiogram in Mobile Devices
IRJET-  	  Hearing Loss Detection through Audiogram in Mobile DevicesIRJET-  	  Hearing Loss Detection through Audiogram in Mobile Devices
IRJET- Hearing Loss Detection through Audiogram in Mobile DevicesIRJET Journal
 
IRJET- Voice Modulation and Verification for Smart Authentication System
IRJET- Voice Modulation and Verification for Smart Authentication SystemIRJET- Voice Modulation and Verification for Smart Authentication System
IRJET- Voice Modulation and Verification for Smart Authentication SystemIRJET Journal
 
IRJET- Comparative Analysis of Emotion Recognition System
IRJET- Comparative Analysis of Emotion Recognition SystemIRJET- Comparative Analysis of Emotion Recognition System
IRJET- Comparative Analysis of Emotion Recognition SystemIRJET Journal
 
IRJET- Segmentation in Digital Signal Processing
IRJET-  	  Segmentation in Digital Signal ProcessingIRJET-  	  Segmentation in Digital Signal Processing
IRJET- Segmentation in Digital Signal ProcessingIRJET Journal
 
IRJET- Voice Command Execution with Speech Recognition and Synthesizer
IRJET- Voice Command Execution with Speech Recognition and SynthesizerIRJET- Voice Command Execution with Speech Recognition and Synthesizer
IRJET- Voice Command Execution with Speech Recognition and SynthesizerIRJET Journal
 
A Review on Speech Enhancement System using FIR Filter
A Review on Speech Enhancement System using FIR FilterA Review on Speech Enhancement System using FIR Filter
A Review on Speech Enhancement System using FIR FilterIRJET Journal
 
Speech Emotion Recognition Using Machine Learning
Speech Emotion Recognition Using Machine LearningSpeech Emotion Recognition Using Machine Learning
Speech Emotion Recognition Using Machine LearningIRJET Journal
 
IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...
IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...
IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...IRJET Journal
 
IRJET- Emotion Recognition from Voice
IRJET- Emotion Recognition from VoiceIRJET- Emotion Recognition from Voice
IRJET- Emotion Recognition from VoiceIRJET Journal
 
Development of Algorithm for Voice Operated Switch for Digital Audio Control ...
Development of Algorithm for Voice Operated Switch for Digital Audio Control ...Development of Algorithm for Voice Operated Switch for Digital Audio Control ...
Development of Algorithm for Voice Operated Switch for Digital Audio Control ...IJMER
 
IRJET- Music Genre Classification using SVM
IRJET- Music Genre Classification using SVMIRJET- Music Genre Classification using SVM
IRJET- Music Genre Classification using SVMIRJET Journal
 
IRJET - Heart Health Classification and Prediction using Machine Learning
IRJET -  	  Heart Health Classification and Prediction using Machine LearningIRJET -  	  Heart Health Classification and Prediction using Machine Learning
IRJET - Heart Health Classification and Prediction using Machine LearningIRJET Journal
 
IRJET- Fault Detection and Maintenance Prediction for Gear of an Industri...
IRJET-  	  Fault Detection and Maintenance Prediction for Gear of an Industri...IRJET-  	  Fault Detection and Maintenance Prediction for Gear of an Industri...
IRJET- Fault Detection and Maintenance Prediction for Gear of an Industri...IRJET Journal
 
Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...IRJET Journal
 
Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...IRJET Journal
 
Music Genre Classification using Machine Learning
Music Genre Classification using Machine LearningMusic Genre Classification using Machine Learning
Music Genre Classification using Machine LearningIRJET Journal
 
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...IRJET Journal
 

Semelhante a VOICE-GENDER (20)

Robust Speech Recognition Technique using Mat lab
Robust Speech Recognition Technique using Mat labRobust Speech Recognition Technique using Mat lab
Robust Speech Recognition Technique using Mat lab
 
IRJET- Musical Instrument Recognition using CNN and SVM
IRJET-  	  Musical Instrument Recognition using CNN and SVMIRJET-  	  Musical Instrument Recognition using CNN and SVM
IRJET- Musical Instrument Recognition using CNN and SVM
 
IRJET- Hearing Loss Detection through Audiogram in Mobile Devices
IRJET-  	  Hearing Loss Detection through Audiogram in Mobile DevicesIRJET-  	  Hearing Loss Detection through Audiogram in Mobile Devices
IRJET- Hearing Loss Detection through Audiogram in Mobile Devices
 
IRJET- Voice Modulation and Verification for Smart Authentication System
IRJET- Voice Modulation and Verification for Smart Authentication SystemIRJET- Voice Modulation and Verification for Smart Authentication System
IRJET- Voice Modulation and Verification for Smart Authentication System
 
IRJET- Comparative Analysis of Emotion Recognition System
IRJET- Comparative Analysis of Emotion Recognition SystemIRJET- Comparative Analysis of Emotion Recognition System
IRJET- Comparative Analysis of Emotion Recognition System
 
IRJET- Segmentation in Digital Signal Processing
IRJET-  	  Segmentation in Digital Signal ProcessingIRJET-  	  Segmentation in Digital Signal Processing
IRJET- Segmentation in Digital Signal Processing
 
IRJET- Voice Command Execution with Speech Recognition and Synthesizer
IRJET- Voice Command Execution with Speech Recognition and SynthesizerIRJET- Voice Command Execution with Speech Recognition and Synthesizer
IRJET- Voice Command Execution with Speech Recognition and Synthesizer
 
A Review on Speech Enhancement System using FIR Filter
A Review on Speech Enhancement System using FIR FilterA Review on Speech Enhancement System using FIR Filter
A Review on Speech Enhancement System using FIR Filter
 
Speech Emotion Recognition Using Machine Learning
Speech Emotion Recognition Using Machine LearningSpeech Emotion Recognition Using Machine Learning
Speech Emotion Recognition Using Machine Learning
 
IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...
IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...
IRJET- Device Activation based on Voice Recognition using Mel Frequency Cepst...
 
IRJET- Emotion Recognition from Voice
IRJET- Emotion Recognition from VoiceIRJET- Emotion Recognition from Voice
IRJET- Emotion Recognition from Voice
 
Development of Algorithm for Voice Operated Switch for Digital Audio Control ...
Development of Algorithm for Voice Operated Switch for Digital Audio Control ...Development of Algorithm for Voice Operated Switch for Digital Audio Control ...
Development of Algorithm for Voice Operated Switch for Digital Audio Control ...
 
IRJET- Music Genre Classification using SVM
IRJET- Music Genre Classification using SVMIRJET- Music Genre Classification using SVM
IRJET- Music Genre Classification using SVM
 
IRJET - Heart Health Classification and Prediction using Machine Learning
IRJET -  	  Heart Health Classification and Prediction using Machine LearningIRJET -  	  Heart Health Classification and Prediction using Machine Learning
IRJET - Heart Health Classification and Prediction using Machine Learning
 
IRJET- Fault Detection and Maintenance Prediction for Gear of an Industri...
IRJET-  	  Fault Detection and Maintenance Prediction for Gear of an Industri...IRJET-  	  Fault Detection and Maintenance Prediction for Gear of an Industri...
IRJET- Fault Detection and Maintenance Prediction for Gear of an Industri...
 
Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...
 
Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...Voice Recognition Based Automation System for Medical Applications and for Ph...
Voice Recognition Based Automation System for Medical Applications and for Ph...
 
Music Genre Classification using Machine Learning
Music Genre Classification using Machine LearningMusic Genre Classification using Machine Learning
Music Genre Classification using Machine Learning
 
50120140505010
5012014050501050120140505010
50120140505010
 
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
 

Mais de IRJET Journal

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...IRJET Journal
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTUREIRJET Journal
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...IRJET Journal
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsIRJET Journal
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...IRJET Journal
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...IRJET Journal
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...IRJET Journal
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...IRJET Journal
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASIRJET Journal
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...IRJET Journal
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProIRJET Journal
 
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...IRJET Journal
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemIRJET Journal
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesIRJET Journal
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web applicationIRJET Journal
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...IRJET Journal
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.IRJET Journal
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...IRJET Journal
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignIRJET Journal
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...IRJET Journal
 

Mais de IRJET Journal (20)

TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
 
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURESTUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
 
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
 
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil CharacteristicsEffect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
 
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
 
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
 
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
 
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
 
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADASA REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
 
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
 
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD ProP.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
 
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
 
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare SystemSurvey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
 
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridgesReview on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
 
React based fullstack edtech web application
React based fullstack edtech web applicationReact based fullstack edtech web application
React based fullstack edtech web application
 
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
 
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
 
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
 
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic DesignMultistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
 
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
 

Último

List of Accredited Concrete Batching Plant.pdf
List of Accredited Concrete Batching Plant.pdfList of Accredited Concrete Batching Plant.pdf
List of Accredited Concrete Batching Plant.pdfisabel213075
 
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...Erbil Polytechnic University
 
Energy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxEnergy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxsiddharthjain2303
 
Comprehensive energy systems.pdf Comprehensive energy systems.pdf
Comprehensive energy systems.pdf Comprehensive energy systems.pdfComprehensive energy systems.pdf Comprehensive energy systems.pdf
Comprehensive energy systems.pdf Comprehensive energy systems.pdfalene1
 
Immutable Image-Based Operating Systems - EW2024.pdf
Immutable Image-Based Operating Systems - EW2024.pdfImmutable Image-Based Operating Systems - EW2024.pdf
Immutable Image-Based Operating Systems - EW2024.pdfDrew Moseley
 
Levelling - Rise and fall - Height of instrument method
Levelling - Rise and fall - Height of instrument methodLevelling - Rise and fall - Height of instrument method
Levelling - Rise and fall - Height of instrument methodManicka Mamallan Andavar
 
11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdf11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdfHafizMudaserAhmad
 
Research Methodology for Engineering pdf
Research Methodology for Engineering pdfResearch Methodology for Engineering pdf
Research Methodology for Engineering pdfCaalaaAbdulkerim
 
FUNCTIONAL AND NON FUNCTIONAL REQUIREMENT
FUNCTIONAL AND NON FUNCTIONAL REQUIREMENTFUNCTIONAL AND NON FUNCTIONAL REQUIREMENT
FUNCTIONAL AND NON FUNCTIONAL REQUIREMENTSneha Padhiar
 
Katarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School CourseKatarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School Coursebim.edu.pl
 
KCD Costa Rica 2024 - Nephio para parvulitos
KCD Costa Rica 2024 - Nephio para parvulitosKCD Costa Rica 2024 - Nephio para parvulitos
KCD Costa Rica 2024 - Nephio para parvulitosVictor Morales
 
Computer Graphics Introduction, Open GL, Line and Circle drawing algorithm
Computer Graphics Introduction, Open GL, Line and Circle drawing algorithmComputer Graphics Introduction, Open GL, Line and Circle drawing algorithm
Computer Graphics Introduction, Open GL, Line and Circle drawing algorithmDeepika Walanjkar
 
Novel 3D-Printed Soft Linear and Bending Actuators
Novel 3D-Printed Soft Linear and Bending ActuatorsNovel 3D-Printed Soft Linear and Bending Actuators
Novel 3D-Printed Soft Linear and Bending ActuatorsResearcher Researcher
 
Paper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdf
Paper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdfPaper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdf
Paper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdfNainaShrivastava14
 
High Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMS
High Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMSHigh Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMS
High Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMSsandhya757531
 
Earthing details of Electrical Substation
Earthing details of Electrical SubstationEarthing details of Electrical Substation
Earthing details of Electrical Substationstephanwindworld
 
Gravity concentration_MI20612MI_________
Gravity concentration_MI20612MI_________Gravity concentration_MI20612MI_________
Gravity concentration_MI20612MI_________Romil Mishra
 
Ch10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdfCh10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdfChristianCDAM
 
Stork Webinar | APM Transformational planning, Tool Selection & Performance T...
Stork Webinar | APM Transformational planning, Tool Selection & Performance T...Stork Webinar | APM Transformational planning, Tool Selection & Performance T...
Stork Webinar | APM Transformational planning, Tool Selection & Performance T...Stork
 
Cost estimation approach: FP to COCOMO scenario based question
Cost estimation approach: FP to COCOMO scenario based questionCost estimation approach: FP to COCOMO scenario based question
Cost estimation approach: FP to COCOMO scenario based questionSneha Padhiar
 

Último (20)

List of Accredited Concrete Batching Plant.pdf
List of Accredited Concrete Batching Plant.pdfList of Accredited Concrete Batching Plant.pdf
List of Accredited Concrete Batching Plant.pdf
 
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
Comparative study of High-rise Building Using ETABS,SAP200 and SAFE., SAFE an...
 
Energy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptxEnergy Awareness training ppt for manufacturing process.pptx
Energy Awareness training ppt for manufacturing process.pptx
 
Comprehensive energy systems.pdf Comprehensive energy systems.pdf
Comprehensive energy systems.pdf Comprehensive energy systems.pdfComprehensive energy systems.pdf Comprehensive energy systems.pdf
Comprehensive energy systems.pdf Comprehensive energy systems.pdf
 
Immutable Image-Based Operating Systems - EW2024.pdf
Immutable Image-Based Operating Systems - EW2024.pdfImmutable Image-Based Operating Systems - EW2024.pdf
Immutable Image-Based Operating Systems - EW2024.pdf
 
Levelling - Rise and fall - Height of instrument method
Levelling - Rise and fall - Height of instrument methodLevelling - Rise and fall - Height of instrument method
Levelling - Rise and fall - Height of instrument method
 
11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdf11. Properties of Liquid Fuels in Energy Engineering.pdf
11. Properties of Liquid Fuels in Energy Engineering.pdf
 
Research Methodology for Engineering pdf
Research Methodology for Engineering pdfResearch Methodology for Engineering pdf
Research Methodology for Engineering pdf
 
FUNCTIONAL AND NON FUNCTIONAL REQUIREMENT
FUNCTIONAL AND NON FUNCTIONAL REQUIREMENTFUNCTIONAL AND NON FUNCTIONAL REQUIREMENT
FUNCTIONAL AND NON FUNCTIONAL REQUIREMENT
 
Katarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School CourseKatarzyna Lipka-Sidor - BIM School Course
Katarzyna Lipka-Sidor - BIM School Course
 
KCD Costa Rica 2024 - Nephio para parvulitos
KCD Costa Rica 2024 - Nephio para parvulitosKCD Costa Rica 2024 - Nephio para parvulitos
KCD Costa Rica 2024 - Nephio para parvulitos
 
Computer Graphics Introduction, Open GL, Line and Circle drawing algorithm
Computer Graphics Introduction, Open GL, Line and Circle drawing algorithmComputer Graphics Introduction, Open GL, Line and Circle drawing algorithm
Computer Graphics Introduction, Open GL, Line and Circle drawing algorithm
 
Novel 3D-Printed Soft Linear and Bending Actuators
Novel 3D-Printed Soft Linear and Bending ActuatorsNovel 3D-Printed Soft Linear and Bending Actuators
Novel 3D-Printed Soft Linear and Bending Actuators
 
Paper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdf
Paper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdfPaper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdf
Paper Tube : Shigeru Ban projects and Case Study of Cardboard Cathedral .pdf
 
High Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMS
High Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMSHigh Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMS
High Voltage Engineering- OVER VOLTAGES IN ELECTRICAL POWER SYSTEMS
 
Earthing details of Electrical Substation
Earthing details of Electrical SubstationEarthing details of Electrical Substation
Earthing details of Electrical Substation
 
Gravity concentration_MI20612MI_________
Gravity concentration_MI20612MI_________Gravity concentration_MI20612MI_________
Gravity concentration_MI20612MI_________
 
Ch10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdfCh10-Global Supply Chain - Cadena de Suministro.pdf
Ch10-Global Supply Chain - Cadena de Suministro.pdf
 
Stork Webinar | APM Transformational planning, Tool Selection & Performance T...
Stork Webinar | APM Transformational planning, Tool Selection & Performance T...Stork Webinar | APM Transformational planning, Tool Selection & Performance T...
Stork Webinar | APM Transformational planning, Tool Selection & Performance T...
 
Cost estimation approach: FP to COCOMO scenario based question
Cost estimation approach: FP to COCOMO scenario based questionCost estimation approach: FP to COCOMO scenario based question
Cost estimation approach: FP to COCOMO scenario based question
 

VOICE-GENDER

  • 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2109 Voice based Gender Recognition Remna R. Nair1, Bhagya Vijayan2 1Master of Computer Applications, College of Engineering, Trivandrum, Kerala, India 2Asst.Professor, Master of Computer Applications, College of Engineering, Trivandrum, Kerala, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - An Is a human’s voice “UNIQUE”? This is actually a good question with which most of us are really confused. Yes!! How much a fingerprint is unique that much a human’s voice is also unique. Because of thisuniquenessofthevoice, the human voice can be used for many recognition processes. One of the most heard recognition processes is “gender”. Itiseasier for an individual to recognize or identify a human gender by hearing the voice. So this paper is developed with a mindset to make the machine learn and identify the gender of the given voice(real-world input). Key Words: Decision Trees, Gradient Tree Boosting, Gender Recognition,Randomforests,SupportVectorMachine(SVM). 1. INTRODUCTION One of the most common means of communication in the world is through voice. In the real world, it is possible for a person to verify the gender of a person through voice. Voice is filled with lots of linguistic features. These voice features are considered as the voice prints to recognize the gender of a speaker. The recorded voice is considered as the input to the system, which then the system process to get voice features. Examine the input and compare it with the trained model, carry out calculations based on the algorithm used and gives the latest matching output.Genderrecognitioncan be used along with various other applications. Some are:  For detecting feeling like male sad, female anger, etc.  Differentiating audios and videos using tags.  Spontaneous salutations.  Helping personal assistants to answer questions with gender-specific results etc. 2. METHODOLOGY The dataset used for detecting gender from the audio files is retrieved from VoxForge, which is a free speech corpus and acoustic model repository foropen source speech engines. It is a large-scale collection of voices of both genders. From the collected audio files the powerful discriminatingfeaturesare extracted with which a CSV file is created. With this CSV file various models are trained using Support Vector Machine, Decision Trees, Gradient Tree Boosting, Random forests,and accuracy is calculated. The goal is to compare outputs of various models and suggest the best model that can be used for gender recognition by voice in real-world inputs. In short, the following are the steps followed -  First, the voice(.wav files) needs to be convertedtoa form that the system can understand.  Preprocessing needs to be done on the file to avoid external noises.  After the noises have been removed the feature extraction process can be carried out. It is much necessary to find out the acoustic features that have a high discriminative power to classify the genders.  Next step, is to train the machine with collected features from the dataset to make the machine capable to classify the genders of the voice. Here the machines are trained with four algorithms Support Vector Machine, Decision tree, Gradient Tree Boosting, and Random Forest.  Calculate the accuracy of each algorithm with the dataset.  After finding out the best algorithm over the dataset (based on the accuracy), a particular algorithm will be used to find out the gender of therealworldinput given while testing. Fig -1: Overall process of the system
  • 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2110 3. IMPLEMENTATION 3.1 Data Collection and Preprocessing For Voice Based Gender Recognition system, the dataset collected consist of 62,440 audio samples compressed (.tgz) in sets of 10 files that can be automatically downloaded from the url http://www.repository.voxforge1.org/downloads/SpeechCo rpus/Trunk/Audio/Main/16kHz_16bit. Next step is to uncompress the compressed files. After uncompressing the .wav files are obtained. These .wav files are not understood by the machines, so it needs to be converted into the machine-understandable format. First, the contents of every wave file are read, then the features are extracted and saved into a pandas data frame. In addition to the wave file, the README files(available with the downloaded dataset) are also parsed to extract metadata: gender, age range, and pronunciation. Notably, the python package Scipywavefileis used to get the audio data, Scipy stats to extract the main features and Numpy and its fast fourier transform fft and fftfreq to deduce the .wav data to frequencies. The data from the .wav files are recorded as amplitude in the time domain, but the potentially valuable features (with a higher discriminative power male/female) are frequencies. To convert the data to frequencies we use DFT (Discrete Fourier Transforms), particularly the FFT implementation (Fast Fourier Transform) of the algorithm. The Fourier transform takes a signal in the time domain (set of measurements over time) and turns it into a spectrum - a set of frequencies with corresponding (complex) values. The spectrum does not contain any information about time! So, to find both the frequencies and the time at which they were recorded, the audio signal is splitted into small, overlapping slices, and the Fourier transform is applied to each (short time Fourier transform).np.fft.fft returns a complex spectrum. np.fft.fftfreq returns the sample frequencies. A sample folder consists of 10 audio recordings from one particular user. Every .wav file in the folder is processed in a way that the dominating frequenciesinsliding windows of 200ms (1/5thofasecond)areextracted.Ifa.wav file is 4 seconds long, a list containing 20 frequencies will be extracted. The list of frequencies is then filtered to contain only values in the human voice range (20Hz < frequency < 280Hz) In addition, values around 50Hzaremostlikelynoise and also filtered (https://en.wikipedia.org/wiki/Mains_hum). 3.2 Feature Extraction The most important featureextracted is the frequencieswith which more powerful detection can be done. The rest of the feature depends on these frequencies. Here, the dominating frequencies are extracted in sliding windows of 200ms.After the dominating frequencies are extracted other properties such as skew, kurtosis, etc are calculated. With the following features a CSV file is created to train the models.  Mean - Mean specifies the average of all the dominating frequencies.  Median - Median is the middle value in the list of frequencies.  Mode - Here, mode refers to the frequency that occurs most often.  Standard Deviation - By calculating the standard deviation we could get how much the values in the dominating frequency list varies from the mean value of the list.  Skewness - Skewness shows the asymmetry of the voice frequencyspectrumaroundthesamplemeans. If skewness is positive, the spectrum spreads out more to the right of the mean than to the left side, and vice versa.  Kurtosis - Kurtosis shows how muchoutlier-pronea distributionis.Thefrequencyspectrumwillexhibita normal shape if kurtosis value is 3.Otherwise if the value is less than 3, the frequency spectrum will have fewer items at the center and the tails than the normal curve but with more items in the shoulders. If the frequency spectrum is having more itemsnear the center and at the tails, and few items in the shoulders compared to a normal distribution with the samemean and variance, then thekurtosisvalue is greater than 3.  Low and High - Low points out the minimum frequency in the dominating frequency list and high shows the maximum frequency in the dominating frequency list.  First Quartile(Q25 ) - Q25 is the median of the lower half of the dominating frequency list.Itmeans that about 25% of the frequency values in the dominating frequency list liebelow Q25 and 75% of dominating frequency values larger than Q25.  Third Quartile(Q75 ) - Q75 is the median of the upper half of the dominating frequency list. It suggests that about 75% of the frequency values in the dominating frequencylistliebelowQ75andonly 25% of dominating frequency values lie above Q75.  Interquartile Range(IQR ) - IQR means the frequency ranging between Q25 and Q75 and the value is the difference between Q75 and Q25 of an audio. 3.3 Modeling Using Different Machine Learning Algorithms The different ML algorithms used are: Support Vector Machine(SVM) - SVM is a discriminative classifier that classifies the dataset into two parts of a hyperplane based on theextractedfeatures.Whenanewdata
  • 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2111 occurs, SVM compares with the existing groups, and with which greater similarity is found it will be binded with that particular group. Decision Trees (DTs) - DTs non-parametric supervised learning method used for classification and regression. The goal is to create a model that predicts the gender by learning simple decision rules inferred from the data features. Gradient Tree Boosting or Gradient Boosted RegressionTrees( GBRT) - Gradient Boosting is a generalization of boosting to arbitrary differentiable loss functions. Random Forest - Random Forest is a supervised classification algorithm. As of the name suggests, this algorithm creates the forest with a number of trees. In Random Forest classifier as the number of the tree increases, the forest gives the high accuracy results. After modeling with these datasets the best algorithm for voice-based gender recognition is identified. With the best model, the real world inputs gender can be identified. 3.4 Testing The Models For testing the models an interface needs to be created for recording human voice. After the human voice has been recorded the noises are cleared out. Then thisrecordedinput is given to the best model(model with high accuracy compared to others) and the gender is detected. 4. RESULT The result is the calculated accuracies from all models. The accuracies with the different models are compared and the best model is the one which has thehighestaccuracywiththe data. The aim of using multiple models is to identify the best gender recognition model,whichcanbehelpfulindeveloping future applications. The table below shows the obtained accuracies of different models. Table -1: Accuracy Table Algorithm Used Training Testing Decision Tree 1.000 0.869 Gradient Boosting 0.958 0.937 Random Forests 0.987 0.893 Support Vector Machine 0.940 0.905 The result points out that the algorithm with the highest accuracy is Random Forest. So the best algorithm for Voice Based Gender Classification is Random Forest. Assessment of the variable importance - Methods that use ensembles of decision trees (Tree, Forest, and Gradient Boosting) can compute the relative importance of each attribute. These importance values can be used to inform a feature selection process. The feature importance depends on how well a feature discriminates between theclasses.Thestd,devseemstobein the top 3 most important features in the three tree-based models. Chart -1: Decision tree classifier Chart -2: Gradient Boosting Classifier Chart -3: Random Forest Classifier
  • 4. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 05 | May 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2112 5. CONCLUSIONS The aim of this paper is to build a gender recognition system based on voice. As stated above std, dev, kurtosis, and skewness seem to have the most discriminant power. Some unexpected behavior is in the peaks at very low frequencies (< 50 Hz) that can be viewed in mode and median. This can be due to the presence of noise in theaudio recordings. Even if it was filtered, not all sources of noise were accounted for and furtheranalysisinthiswaywould be interesting but falls beyond the scope of this project. Further exploration of potentiallyinterestingfeaturescould also be pictured out. Other features that were not used here but could also have good differentiating power are: spectral flatness spectral entropy, fundamental frequency At the same time, the set of selected features seem to be enough for the tested models to achieve good accuracy. The Random Forest gave the best accuracy followed by the GradientBoosting, SVM and Decision Tree. As for the applicability of the tested models, the analysis of this dataset was supervised and one might not always have access to the labels of the different categories.Buttheycould be of great utility in a variety of situations, like discerning music/speech or a correctly functioning machine/instrument from a faulty one. REFERENCES [1] H. Harb and L. Chen, “Voice-based gender identification in multimedia applications,” Journal of Intelligent Information Systems, vol.24,no.2-3,pp.179–198,2005. [Online]. Available: http://dx.doi.org/10.1007/s10844- 005-0322-8. [2] Kunyu Chen, Gender Identification By Voice, Stanford University kunyu@stanford.edu. [3] T. Vogt and E. André, “Improving automatic emotion recognition from speech via gender differentiation,” in Proc. Language Resources and Evaluation Conference (LREC 2006), Genoa. Citeseer, 2006.