Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition

Dipayan Bhadra; Mehrab Hosain; Fatema Alam

doi:10.5281/zenodo.15794199

Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition

Audio and Speech Processing 2025-08-12 v1 Sound

Authors: Dipayan Bhadra , Mehrab Hosain , Fatema Alam

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

As the most important human-machine interfacing tool, an insignificant amount of work has been carried out on Bangla Speech Recognition compared to the English language. Motivated by this, in this work, the performance of speaker-independent isolated speech recognition systems has been implemented and analyzed using a dataset that is created containing both isolated Bangla and English spoken words. An approach using the Mel Frequency Cepstral Coefficient (MFCC) and Deep Feed-Forward Fully Connected Neural Network (DFFNN) of 7 layers as a classifier is proposed in this work to recognize isolated spoken words. This work shows 93.42% recognition accuracy which is better compared to most of the works done previously on Bangla speech recognition considering the number of classes and dataset size.

Keywords

speech and audio processing speaker recognition and verification

Cite

@article{arxiv.2507.07068,
  title  = {Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition},
  author = {Dipayan Bhadra and Mehrab Hosain and Fatema Alam},
  journal= {arXiv preprint arXiv:2507.07068},
  year   = {2025}
}

Comments

12 pages, 3 figures, 4 tables. published in Jatiya Kabi Kazi Nazrul Islam University, Vol. 10 No. 1-2, 2025 https://jkkniu.edu.bd/13817-2/

Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition

Abstract

Keywords

Cite

Comments

Related papers