BanglaNum -- A Public Dataset for Bengali Digit Recognition from Speech

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mohammad, Mir Sayeed, Zahid, Azizul, Iqbal, Md Asif
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910375741489152
author Mohammad, Mir Sayeed
Zahid, Azizul
Iqbal, Md Asif
author_facet Mohammad, Mir Sayeed
Zahid, Azizul
Iqbal, Md Asif
contents Automatic speech recognition (ASR) converts the human voice into readily understandable and categorized text or words. Although Bengali is one of the most widely spoken languages in the world, there have been very few studies on Bengali ASR, particularly on Bangladeshi-accented Bengali. In this study, audio recordings of spoken digits (0-9) from university students were used to create a Bengali speech digits dataset that may be employed to train artificial neural networks for voice-based digital input systems. This paper also compares the Bengali digit recognition accuracy of several Convolutional Neural Networks (CNNs) using spectrograms and shows that a test accuracy of 98.23% is achievable using parameter-efficient models such as SqueezeNet on our dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13465
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BanglaNum -- A Public Dataset for Bengali Digit Recognition from Speech
Mohammad, Mir Sayeed
Zahid, Azizul
Iqbal, Md Asif
Audio and Speech Processing
Signal Processing
Automatic speech recognition (ASR) converts the human voice into readily understandable and categorized text or words. Although Bengali is one of the most widely spoken languages in the world, there have been very few studies on Bengali ASR, particularly on Bangladeshi-accented Bengali. In this study, audio recordings of spoken digits (0-9) from university students were used to create a Bengali speech digits dataset that may be employed to train artificial neural networks for voice-based digital input systems. This paper also compares the Bengali digit recognition accuracy of several Convolutional Neural Networks (CNNs) using spectrograms and shows that a test accuracy of 98.23% is achievable using parameter-efficient models such as SqueezeNet on our dataset.
title BanglaNum -- A Public Dataset for Bengali Digit Recognition from Speech
topic Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2403.13465