Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)

Estimating the age and gender of the speaker has gained great importance in recent years due to its necessity in various commercial, medical and forensic applications. This work estimates the speakers gender and ages in small range of years where every ten years has been divided into two subcategor...

Full description

Saved in:
Bibliographic Details
Main Authors: Aalaa Ahmed Mohammed, Yusra Faisal Al-Irhayim
Format: Article
Language:English
Published: Tikrit University 2021-07-01
Series:Tikrit Journal of Pure Science
Subjects:
Online Access:https://tjpsj.org/index.php/tjps/article/view/166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426852404264960
author Aalaa Ahmed Mohammed
Yusra Faisal Al-Irhayim
author_facet Aalaa Ahmed Mohammed
Yusra Faisal Al-Irhayim
author_sort Aalaa Ahmed Mohammed
collection DOAJ
description Estimating the age and gender of the speaker has gained great importance in recent years due to its necessity in various commercial, medical and forensic applications. This work estimates the speakers gender and ages in small range of years where every ten years has been divided into two subcategories for a span of years extending from teens to sixties. A system of speaker age and gender estimation uses Mel Frequency Cepstrum Coefficient (MFCC) as a features extraction method, and Bidirectional Long-Short Term Memory (BiLSTM) as a classification method.  Two models of two deep neural networks were building, one for speaker age estimation, and the other for speaker gender estimation. The experimental results show that the deep neural network model of age estimation achieves 94.008 % as accuracy rate, while the deep neural network model of gender estimation achieves 90.816% as accuracy rate.
format Article
id doaj-art-7a4e6787cdb7466c982f4d406b9849ac
institution Kabale University
issn 1813-1662
2415-1726
language English
publishDate 2021-07-01
publisher Tikrit University
record_format Article
series Tikrit Journal of Pure Science
spelling doaj-art-7a4e6787cdb7466c982f4d406b9849ac2025-08-20T03:29:14ZengTikrit UniversityTikrit Journal of Pure Science1813-16622415-17262021-07-0126410.25130/tjps.v26i4.166Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)Aalaa Ahmed MohammedYusra Faisal Al-Irhayim Estimating the age and gender of the speaker has gained great importance in recent years due to its necessity in various commercial, medical and forensic applications. This work estimates the speakers gender and ages in small range of years where every ten years has been divided into two subcategories for a span of years extending from teens to sixties. A system of speaker age and gender estimation uses Mel Frequency Cepstrum Coefficient (MFCC) as a features extraction method, and Bidirectional Long-Short Term Memory (BiLSTM) as a classification method.  Two models of two deep neural networks were building, one for speaker age estimation, and the other for speaker gender estimation. The experimental results show that the deep neural network model of age estimation achieves 94.008 % as accuracy rate, while the deep neural network model of gender estimation achieves 90.816% as accuracy rate. https://tjpsj.org/index.php/tjps/article/view/166speaker age estimationspeaker gender estimationMFCCBiLSTM
spellingShingle Aalaa Ahmed Mohammed
Yusra Faisal Al-Irhayim
Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)
Tikrit Journal of Pure Science
speaker age estimation
speaker gender estimation
MFCC
BiLSTM
title Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)
title_full Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)
title_fullStr Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)
title_full_unstemmed Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)
title_short Speaker Age and Gender Estimation Based on Deep Learning Bidirectional Long-Short Term Memory (BiLSTM)
title_sort speaker age and gender estimation based on deep learning bidirectional long short term memory bilstm
topic speaker age estimation
speaker gender estimation
MFCC
BiLSTM
url https://tjpsj.org/index.php/tjps/article/view/166
work_keys_str_mv AT aalaaahmedmohammed speakerageandgenderestimationbasedondeeplearningbidirectionallongshorttermmemorybilstm
AT yusrafaisalalirhayim speakerageandgenderestimationbasedondeeplearningbidirectionallongshorttermmemorybilstm