Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Exploring Bengali speech for gender classification: machine learning and deep learning approaches

Bulletin of Electrical Engineering and Informatics · Vol. 14 No. 1 (2024) · hlm. 328–337

DOI
10.11591/eei.v14i1.8146
ISSN
2089-3191, 2302-9285
Terbit
2024-11-22
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Speech enables clear and powerful idea transmission. The human voice, rich in tone and emotion, holds unique beauty and significance in daily life. Vocal pitches vary by gender and are influenced by emotions and languages. While people naturally perceive these nuances, machines often struggle to capture these subtle distinctions. Machines may struggle to detect these nuances, but people effortlessly perceive them. This project aims to use various machine learning (ML) and deep learning (DL) techniques to reliably determine an individual’s gender from a corpus of Bengali conversations. Our dataset comprises 3185 Bengali speeches, with 1100 delivered by males, 1035 by women, and 1050 by those who identify as third gender. We employed six distinct feature extraction techniques to examine the audio data: roll-off, spectral centroid, chroma-stft, spectral bandwidth, zero crossing rate, and Mel-frequency cepstral coefficients (MFCC). Extreme gradient boosting (XGBoost), support vector machines (SVM), K-nearest neighbors (KNN), decision trees classifier (DTC), and random forest (RF) were employed as the five ML algorithms to comprehensively analyze the dataset. For a full study, we also included 1D convolutional neural networks (CNN) from the DL area. The 1D CNN performed extraordinarily well, exceeding the accuracy of all other algorithms with a stunning 99.37%.

Kata kunci

Jaringan kolaborasi para penulis

13 penulis · 34 tautan kepenulisan bersama · 21 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Daffodil International University
  • Independent University, Bangladesh
  • Bangladesh University
  • Western Sydney University
  • Pace University
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Md. Tarek HabibIndependent University, Bangladesh2
Md. Ariful Islam ArifDaffodil International University1
Saiful Islam SanyDaffodil International University1
Farah SharminDaffodil International University1
Mohammad Monirul IslamDaffodil International University1
Md. Ataur RahmanIndependent University, Bangladesh1
Mahady HasanIndependent University, Bangladesh1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Exploring Bengali speech for gender classification: machine learning and deep learning approaches</dc:title><dc:creator>Habiba Dewan Arpita</dc:creator><dc:creator>Abdullah Al Ryan</dc:creator><dc:creator>Md. Fahad Hossain</dc:creator><dc:creator>Md. Sadekur Rahman</dc:creator><dc:creator>Md Sajjad</dc:creator><dc:creator>Nuzhat Noor Islam Prova</dc:creator><dc:subject>gender classification</dc:subject><dc:subject>Bengali speech</dc:subject><dc:subject>audio feature extraction</dc:subject><dc:subject>Mel-frequency cepstral coefficients</dc:subject><dc:subject>spectral properties</dc:subject><dc:subject>1D convolutional neural network</dc:subject><dc:subject>XGBoost</dc:subject><dc:subject>random forest</dc:subject><dc:description xml:lang="en">Speech enables clear and powerful idea transmission. The human voice, rich in tone and emotion, holds unique beauty and significance in daily life. Vocal pitches vary by gender and are influenced by emotions and languages. While people naturally perceive these nuances, machines often struggle to capture these subtle distinctions. Machines may struggle to detect these nuances, but people effortlessly perceive them. This project aims to use various machine learning (ML) and deep learning (DL) techniques to reliably determine an individual’s gender from a corpus of Bengali conversations. Our dataset comprises 3185 Bengali speeches, with 1100 delivered by males, 1035 by women, and 1050 by those who identify as third gender. We employed six distinct feature extraction techniques to examine the audio data: roll-off, spectral centroid, chroma-stft, spectral bandwidth, zero crossing rate, and Mel-frequency cepstral coefficients (MFCC). Extreme gradient boosting (XGBoost), support vector machines (SVM), K-nearest neighbors (KNN), decision trees classifier (DTC), and random forest (RF) were employed as the five ML algorithms to comprehensively analyze the dataset. For a full study, we also included 1D convolutional neural networks (CNN) from the DL area. The 1D CNN performed extraordinarily well, exceeding the accuracy of all other algorithms with a stunning 99.37%.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2024-11-22</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v14i1.8146</dc:identifier><dc:identifier>10.11591/eei.v14i1.8146</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 14 No 1 (2024); 328-337</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/8146/4181</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>