International Journal of Computer Engineering and Applications,

Volume XV, Issue V, May 2021, www.ijcea.com ISSN 2321-3469

IDENITIFCATION OF GENDER BASED ON VOICE SIGNALS

G Ramya Sri 1, Dr. M. Sree vani 2
1
Student, Department of Computer Science & Engineering, Mahatma Gandhi Institute of Technology
2
Professor, Department of Computer Science & Engineering, Mahatma Gandhi Institute of
Technology

ABSTRACT:
Gender classification is one among the major speech analysis problems. The acoustic features
of humans are based on genders due to physiological changes in glottis, vocal track thickness
and length. The length of vocal cord for male speaker is longer than that of female speaker, it
means the length of vocal fold is gender dependent. Because of the longer vocal folds male
voice have more intensity. Based on this idea, features of frequency of voice signals will be
differentiated. So, the aim of this paper is to classify gender based on voice signals using
Machine Learning algorithms.

Keywords: Logistic Regression, Decision Tree, Support Vector Machine, Naïve Bayes
Classifier, k-Nearest Neighbors.

[1] INTRODUCTION
Speech signals possess different types of information. Speech recognition, which
provides information about the content of speech signals. Speaker recognition consists
information about the speaker identity. Emotion recognition delivers information about the
speaker’s emotional state. Health recognition offers information on the patient’s health status.
Language recognition yields information of the spoken language. Accent recognition produces
information about the speaker accent. Age recognition gives information about the speaker age.
Gender recognition carries information about the speaker gender [1]. Gender recognition plays
a vital role in Speech signal processing. Using machine learning algorithms, gender of an
individual are often identified based on voice. Automatic gender recognition is the process of
recognizing whether the speaker is a male or female.

G Ramya Sri and Dr. M. Sree vani 1

 IDENITIFCATION OF GENDER BASED ON VOICE SIGNALS

[2] STATE OF THE ART

R. Shiva Shankar, J. Raghaveni , Pravallika Rudraraju , Y.Vineela Sravya: In this paper

[2], authors described about the design of system that determines the speaker gender using the
pitch of the speaker's voice. Authors trained models to classify gender into male or female
based on the voice dataset containing various attributes related to voice like pitch, frequency
etc. The authors of this paper employed the most effective algorithm among K-nearest
neighbours (KNN), Random Forest, Logistic Regression, Decision Tree, support vector
machine and gradient boosting to detect the gender of the speaker with maximum possible
efficiency and accuracy.
Steve Jadav: In this paper [3], author described about classifying gender using various
image classification techniques which usually includes information extraction from a collection
of images. However, gender classification using vocal features has recently been a topic of
interest to a lot of researchers across the world. A detailed scrutiny of some of the human vocal
features reveals that classifying gender goes way beyond just the frequency and also the pitch
of a person. Feature selection or dimensionality reduction method were used. A similar problem
is faced while deciding gender-specific traits-which serve a significant purpose in classifying
the gender of a person. This paper had inspected the efficiency and significance of machine
learning algorithms to the voice-based gender identification problem.
A Raahul, R Sapthagiri, K Pankaj and V Vijayarajan: In this paper [4], authors tried to
trace the gender from acoustic data i.e., pitch, median, frequency etc. Machine learning gives
promising results for classification problem in all the research domains. There are several
performance metrics to judge algorithms of an area. Authors evaluated five different machine
learning algorithms based on eight different metrics in gender classification from acoustic data.
The objective of this paper was to identify gender, with five different algorithms, Linear
Discriminant Analysis (LDA), 4 K-Nearest Neighbour (KNN), Classification and Regression
Trees (CART), Random Forest (RF), and Support Vector Machine (SVM) on basis of eight
different metrics. The main parameter in evaluating any algorithms is its performance. With
this comparative model algorithm, authors were tried to assess the various ML algorithms and
found the best fit for gender classification of acoustic data.
Hadi harb, Liming chen: In this paper [5], authors tried to classify gender based on speech
signal within the context of content-based multimedia indexing. In this paper a set of acoustic
and pitch features along with different classifiers were compared for the problem of gender
identification. The authors shown that the fusion of features and classifiers performs better than
any individual classifier. Based on such conclusions authors built a system for gender
identification in multimedia applications. The system uses a set of Neural Networks with
acoustic and Pitch related features. 90 % of classification accuracy is obtained for 1 second
segments and with independence to the language and the channel of the speech. Practical
considerations, such as the continuity of speech and the use of mixture of experts rather than
one single expert were shown to enhance the classification accuracy to 93%. When used on a
subset of the Switchboard database, the classification accuracy attains 98.5 % for 5 seconds
segments.
Remna R. Nair1, Bhagya Vijayan: In this paper [6] authors described about the system
to differentiate the gender of humans. Because of the uniqueness of the voice, the human voice
can be used for many recognition processes. One of the most heard recognition processes is

G Ramya Sri and Dr. M. Sree vani 2

 International Journal of Computer Engineering and Applications,
Volume XV, Issue V, May 2021, www.ijcea.com ISSN 2321-3469

“gender”. It is easier for an individual to recognize or identify a person’s gender by hearing the
voice. This paper was developed with a mindset to make the machine learn and identify the
gender of the given voice (real-world input). The different machine learning algorithms like
Support vector machine, Decision tree, Gradient Boosting, Random forest were used.

[3] PROBLEM DEFINITION

The main objective of this paper is to identify the gender whether it is male or female
based on voice signal. The acoustic features like mean, median, mode, spectral entropy, spectral
flatness, skew, kurtosis, etc. are extracted from the audio file. These features of audio file are
compared with the dataset which is employed for training the classification models.

Advantages
 Feature selection is performed to identify relevant features.
 Training and testing the data with different classification algorithms.
 Applying the classification models on extracted features from new audio file.

[4] METHODOLOGY
The system basically takes the input file as audio file. Then extract acoustic features in
the form of numerical from the audio file. Then train and test the various classification
algorithms with available dataset. Then evaluate the accuracy for each algorithm and compare
to find best fit model. Using this model, predict the gender of person with new audio file.

Figure:1. System Architecture

[Figure-1] shows the system architecture which defines sequence of steps involved that
is data collection, data pre-processing, training and testing the data on various classification
algorithms and identifying gender.

[4.1] DATA COLLECTION AND DATA PREPROCESSING

G Ramya Sri and Dr. M. Sree vani 3

 IDENITIFCATION OF GENDER BASED ON VOICE SIGNALS

The dataset used to train the model is voice.csv dataset which has 20 features, 1 target
label and 3168 observations.
The features in voice.csv dataset are as following:

 meanfreq: mean frequency (in kHz) which defines the average of all the frequencies.
 sd: standard deviation of frequency defines how much the frequency values in the list varies
from the mean of the list.
 median: median frequency (in kHz) which defines the value separating the upper half from
the lower half of frequency list.
 Q25: first quartile (in kHz) which defines the median of lower half of frequency list
i.e.,25% frequencies are lower than Q25 and 75% frequencies are above Q25.
 Q75: third quartile (in kHz) which defines the median of upper half of frequency list
i.e.,75% frequencies are lower than Q75 and 25% frequencies are above Q75.
 IQR: interquartile range (in kHz) defines the difference between third quartile and first
quartile.
 skew: skewness defines the measure of the asymmetry of the frequency. It can be negative,
positive and zero. If skewness is positive, the spectrum spreads out more to the right of the
mean than to the left side. If skewness is negative, the spectrum spreads out more to the
left of the mean than to the right side. If skewness is zero, it is symmetric about mean.
 kurt: kurtosis defines the measure of combined weight of distribution tail relative to the
centre of distribution.
 sp.ent: spectral entropy defines the measure of disorganisation of frequency.
 sfm: spectral flatness defines the measure of similarity of the spectrum to noise.
 mode: mode frequency defines the frequency which occurs maximum number times.
 centroid: spectral centroid defines a measure used in digital signal processing to
characterise a spectrum.
 peakf: peak frequency defines the frequency with highest energy.
 meanfun: average of fundamental frequency measured across acoustic signal
 minfun: minimum fundamental frequency measured across acoustic signal.
 maxfun: maximum fundamental frequency measured across acoustic signal.
 meandom: average of dominant frequency measured across acoustic signal.
 mindom: minimum of dominant frequency measured across acoustic signal.
 maxdom: maximum of dominant frequency measured across acoustic signal
 dfrange: range of dominant frequency measured across acoustic signal.
 modindx: modulation index. Calculated as the accumulated absolute difference between
adjacent measurements of fundamental frequencies divided by the frequency range.
 label: male or female.
Data pre-processing is the process of cleaning and transform of raw inputs before
processing and analysis. Data cleaning involves identifying missing values and filling them
with mean value of attribute. Data cleaning is performed to voice.csv dataset before training.
The dataset is split into train and test sets. Feature selection is the process where we select the
features which are more appropriate for classification or prediction, automatically or manually.
Mean of frequency, standard deviation, spectral entropy, skew, kurtosis, spectral flatness, Q25,
Q75, IQR, median features are selected. The remaining attributes are depended on these
attributes.

G Ramya Sri and Dr. M. Sree vani 4

 International Journal of Computer Engineering and Applications,
Volume XV, Issue V, May 2021, www.ijcea.com ISSN 2321-3469

Audio file need to be converted into discrete data to extract features of acoustic signal.
The frequency in audio file is in continuous form. By sampling, the continuous signal is
converted to discrete sequence of frequencies. The sampling is done on audio file. The
sampling frequency or sampling rate of sound wave defines the frequency at which amplitudes
are captured. Fourier transformation is a mathematical concept used to convert continuous
signal from time-domain to frequency domain. Fast Fourier transformation is similar to Fourier
transformation, but takes input as discrete signal. Fast Fourier Transform calculates Discrete
Fourier Transform (DFT) of a given sequence. Discrete Fourier Transform converts a sequence
of discrete signal into its frequency constituents. DFT or FFT algorithm convert time domain
discrete signal to frequency domain. Spectral and frequency values at each amplitude are
calculated using discrete Fourier transform.

[4.2] LOGISTIC REGRESSION

Logistic regression is a classification algorithm, used when the value of the target
variable is categorial in nature. It is supervised learning algorithm used to find probability of a
target variable that given data entry belongs to the particular target class. Logistic regression
models the data using the sigmoid function. Binomial logistic regression is used as the target
variable(label) is of two labels 0 (male) and 1(female).

[4.3] SUPPORT VECTOR MACHINE (SVM)

Support vector machine is a classification algorithm. The main objective of Support

vector machine algorithm is to find a hyperplane in an N-dimensional space that distinctly
classifies the data points. It comes under supervised learning. The hyperplane classifies the
target variable or data points. The data points which are on either side of hyperplane create the
class. The dimension of the hyperplane depends upon the number of features. If the number of
input features is two, then the hyperplane is just a line. If the number of input features is three,
then the hyperplane becomes a 2-D plane. The SVM kernel is a function that takes low
dimensional input space and transforms it into higher dimensional space i.e., it converts not
separable problem to separable problem. It is mostly useful in non-linear separation problems.
Simply put the kernel, it does some extremely complex data transformations then finds out the
process to separate the data based on the labels or outputs defined. Linear Kernel is used when
the data is linearly separable, that is, it can be separated using a single line. It is one of the most
common kernels to be used. It is mostly used when there are a large number of features in a
particular dataset. As there are 20 features in voice.csv dataset, Linear kernel is used.

[4.4] DECISION TREE

Decision tree is a classification algorithm and supervised learning algorithm. Decision

tree uses the tree representation to solve the problem in which each leaf node corresponds to a
class label and attributes are represented on the internal node of the tree and the branch
represents a decision rule. To build a decision following steps has to be done.
 Find the best attribute and place it on the root node of the tree.

G Ramya Sri and Dr. M. Sree vani 5

 IDENITIFCATION OF GENDER BASED ON VOICE SIGNALS

 Split the training set of the dataset into subsets. While making the subset make sure that
each subset of training dataset should have the same value for an attribute.
 Find leaf nodes in all branches by repeating above steps on each subset. The root node and
internal nodes can be selected using Gini index method, Information gain method, Entropy
method.
Gini index method is default method used to select root from n attributes of the dataset
which attribute would be placed at the root node or the internal node. Gini index is a metric to
measure how often a randomly chosen attribute would be incorrectly identified. It means an
attribute with lower gini index should be preferred.
[4.5] K-NEAREST NEIGHBOURS (KNN)

K-Nearest Neighbours is classification algorithms in Machine Learning. It belongs to the

supervised learning domain and lazy learning by its nature. It finds intense application in
pattern recognition, data mining. Predictions are done for a point by searching the training set
for the K most points which are similar and predicts the target variable for the K points. To
determine the similarity between K points or instances distance is measured. The distance can
be calculated using Euclidean distance, Manhattan distance, Minkowski distance. K can be kept
as an odd number so that we can calculate a clear majority in the case where only two groups
are possible(male/female).

[4.6] NAÏVE BAYES CLASSIFIER

Naïve Bayes classifier is a classification technique based on Bayes theorem with the
assumption of independence among predictors. Naïve Bayes classifiers assume that the
presence of a particular feature in a class is unrelated to the presence of any other feature or
that all of these properties have independent contribution to the probability. Naïve Bayes
theorem is not a single algorithm but a combination of algorithms where all of them share a
common principle, i.e., every pair of features being classified is independent of each other.
Bayes theorem is calculated as
P(C/x) = P(C)*P(x/C) / P(x)
Where P(C) is class prior probability, P(x) is predictor prior probability, P(x/C) is
likelihood and P(C/x) is posterior probability.
The following steps has to be performed.

 Convert the dataset into frequency table

 Create Likelihood table by finding the probabilities.
 Using Naïve bayes equation calculate posterior probability for each class
The class with highest posterior probability is considered as class of that particular values of
features.

[5] RESULTS
The accuracy of different classification models is calculated and compared. The model
with highest accuracy is considered as best classification model for voice data. The accuracies
are shown in below [Table 1].

G Ramya Sri and Dr. M. Sree vani 6

 International Journal of Computer Engineering and Applications,
Volume XV, Issue V, May 2021, www.ijcea.com ISSN 2321-3469

Table 1 Accuracy Table

Classifiers Accuracy
Logistic Regression 86%
Support Vector 89%
Machine
Decision Tree 76%
K- Nearest 93%
Neighbours
Naïve Bayes 85%

The features are extracted from Voice record or audio file which is in the form of
continuous frequencies. So, it is need to transform into discrete data. The sampling is done on
audio file. The sampling frequency or sampling rate of sound wave defines the frequency at
which amplitudes are captured.
The audio file is represented in amplitude and time graph to differentiate between
different voice signals visually.

Figure:2. Representation of male voice signal

Figure:3. Representation of female voice signal

G Ramya Sri and Dr. M. Sree vani 7

 IDENITIFCATION OF GENDER BASED ON VOICE SIGNALS

The frequencies of signals are plotted in graph as shown in [Figure-2] and [Figure-3].
The gender of particular voice signal is identified using the extracted features from
corresponding voice signals.

[6] CONCLUSION
The ultimate aim is to generate a system which can able to identify gender whether it is
male or female based on voice signals. There are many usages from gender recognition. Some
of them are Biometric purpose, Mobile healthcare system, Remote access to computers,
Automatic transfer of phone call. The acoustic features are selected and trained on various
classification algorithms. Among them decision tree shown good accuracy. So, gender of new
audio file is identified through Decision tree model.Further some more classification
algorithms can be trained and compared to get more appropriate model. The features can be
selected using some other feature selection method. The audio file should be recorded without
noise and disturbance to get accurate results.

G Ramya Sri and Dr. M. Sree vani 8

 International Journal of Computer Engineering and Applications,
Volume XV, Issue V, May 2021, www.ijcea.com ISSN 2321-3469

REFERENCES

[1] Ali Bou Nassif, Ismail Shahin, Imtinan Attili, Mohammad Azzeh, and Khaled Shaalan,
“Speech Recognition Using Deep Neural Networks: A Systematic Review”, IEEE, 2019
[2] R. Shiva Shankar, J. Raghaveni , Pravallika Rudraraju , Y.Vineela Sravya, “Classification
of Gender by Voice Recognition using Machine Learning Algorithms”, International Journal
of Advanced Science and Technology,2020
[3] Steve Jadav, “Voice-Based Gender Identification Using Machine Learning”, International
Conference on Computing Communication and Automation, IEEE, 2018
[4] A Raahul, R Sapthagiri, K Pankaj and V Vijayarajan, “Voice based gender classification
using machine learning”, IOP Publishing, 2017
[5] Hadi harb, Liming chen, “Voice - based gender identification in Multimedia
applications”,2016
[6] Remna R. Nair1, Bhagya Vijayan, “Voice based Gender Recognition”, IRJET, 2019
[7] Francois Pachet, Pierre Roy, “Analytical Features: A knowledge-based approach to audio
features generation”, EURASIP journal on Audio, Speech and Music processing,2009
[8] Shai Shalev-Shwartz, Shai Ben-David, “Understanding Machine learning”, Cambridge
university press, 2014
[9] K.R. Rao, D.N. Kim, J.J. Hwang, “The Fast Fourier Transform algorithm and applications
Springer”, 2010
[10] Julius O. Smith, “Spectral audio signal processing”, W3K, 2011

G Ramya Sri and Dr. M. Sree vani 9