Scribd
Upload
122 views

Voice Recognition Using Machine Learning PDF

This document summarizes research on using machine learning algorithms to detect gender based on voice and speech recognition. A dataset of 3168 labeled voice samples was collected and 21 acoustic features were extracted from each sample. Three machine learning classifiers - Decision Tree, Random Forest, and Logistic Regression - were applied to the dataset, with Random Forest achieving the highest accuracy of 98.5% for gender classification. The research demonstrates that machine learning can effectively classify gender based on voice biometrics, with performance varying based on the specific algorithm and dataset used.

Uploaded by

Mohammed Wahhab
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
122 views

Voice Recognition Using Machine Learning PDF

This document summarizes research on using machine learning algorithms to detect gender based on voice and speech recognition. A dataset of 3168 labeled voice samples was collected and 21 acoustic features were extracted from each sample. Three machine learning classifiers - Decision Tree, Random Forest, and Logistic Regression - were applied to the dataset, with Random Forest achieving the highest accuracy of 98.5% for gender classification. The research demonstrates that machine learning can effectively classify gender based on voice biometrics, with performance varying based on the specific algorithm and dataset used.

Uploaded by

Mohammed Wahhab
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

Al-Nahrain University

College of Information Engineering and Communications


Department of Information Engineering and Communications

Gender Detection Based on Voice and Speech Recognition Using


Different Machine Learning Algorithms

By:
Mohammed Wahhab Abdulrazzaq
Introduction

 Each vocal sound has physical characteristics that can be


related to perceptual evaluations of that sound.

 Frequency (measured in Hertz, Hz), sound level (measured in


decibels, dB), acoustic characteristics.

 Here we will be focused only on the measurement of physical


characteristics of the sound (Acoustic)
Natural Sound Generation
Dataset
 In order to analyze gender by voice and speech, a
training database is required.

 A database was built using 3168 of samples of male and


female voices, each labeled by their gender of male or
female.

 This Dataset contains 3168 rows and 21 columns (20


columns for each feature and one label column for the
classification of male or female).
Dataset Cont..
 The voice physical characteristics (Acoustic) are
obtained using Specan function using Warble package
in R language.

 Meanfreq, Sd, Median, Q25, Q75, IQR, Skew, kurt,


sp.ent, sfm, Mode centroid, meanfun, minfun, maxfun,
meandom, mindom, minidom, maxdom, dfrange,
modindx.
Machine Learning Classification
 Decision Tree Classification

 supervised learning method used


for classification and regression.
 The goal is to create a model that predicts the value of a
target variable by learning simple decision rules inferred
from the data features.

 Decision tree algorithms: ID3 , C4.5 , C5.0, CART


Machine Learning Classification Cont..
Random Forest Classification
 Random forest, like its name implies, consists
of a large number of individual decision trees
that operate as an ensemble.

 Each individual tree in the random forest


spits out a class prediction and the class with
the most votes become our model’s
prediction.
Machine Learning Classification Cont..
Logistic Regression Classification
 statistical model (also known as logit model) is often
used for classification and predictive
 the outcome is a probability, the dependent variable is
bounded between 0 and 1
Steps of Programming and Running
 Python language in Anaconda software and
Jupyter model
1. Reading the Dataset

2. Checking the Dataset if it has missing values

3. Importing classifier

4. Applying machine training on 80% of the dataset


Steps of Programming and Running

5. Making Prediction for the rest 20% of dataset

6. Measuring the accuracy

7. Drawing the confusion matrix

8. Comparing the results of all the used classifiers

9. Testing the machine using new unseen and unlabeled


dataset
Results
 Decision Tree
Accuracy: 97.3186119873817
Confusion Matrix
Results
 Random Forest
Accuracy: 98.58044164037855
Confusion Matrix
Results
 Decision Tree
Accuracy: 92.74447949526814
Confusion Matrix
Conclusions
 Human can make a decision for something but with limited
volume.
 The machine intervention is required when the data are huge but
should be trained perfectly by the human.
 The supervised machine learning algorithms can be used for
doing that purpose through classifying the input data.
 In this project, three supervised machine learning classifiers
(Decision Tree, Random Forest, and Logistic Regression) applied
on the same voice dataset and we got different accuracy values.
 The results sows the best one is the Random Forest algorithm
with accuracy 98.5, while the others are 97.7 for the Decision
Tree algorithm, and finally 92.7 for the Logistic Regression.
 The accuracy of classification differs according to the type and
size of dataset.
THANK YOU

You might also like