Please use this identifier to cite or link to this item:
https://hdl.handle.net/1959.11/55459
Title: | A Comparison of LSTM and GRU for Bengali Speech-to-Text Transformation |
---|---|
Contributor(s): | Jahan, Nusrat (author); Sultana, Zakia (author); Chowdhury, Fahim (author); Ahmed, Sajjad (author); Parvez, Mohammad Zavid (author); Barua, Prabal Datta (author); Chakraborty, Subrata (author)![]() |
Publication Date: | 2023 |
DOI: | 10.1007/978-3-031-33743-7_18 |
Handle Link: | https://hdl.handle.net/1959.11/55459 |
Abstract: | This paper represents an approach to speech-to-text conversion in the Bengali language. In this area, we have found most of the methodologies were focused on other languages rather than Bengali. We started with a novel dataset of 56 unique words from 160 individual subjects was prepared. Then in this paper, we illustrate the approach to increasing accuracy in a speech-to-text over the Bengali language where initially we started with Gated Recurrent Unit(GRU) and Long short-term memory (LSTM) algorithms. During further observation, we found that the output of the GRU failed to give any stable output. So, we moved completely to the LSTM algorithm where we achieved 90% accuracy on an unexplored dataset. Voices of several demographic populations and noises were used to validate the model. In the testing phase, we tried a variety of classes based on their length, complexity, noise, and gender variant. Moreover, we expect that this research will help to develop a real-time Bengali speak-to-text recognition model. |
Publication Type: | Conference Publication |
Conference Details: | ACR 2023: International Conference on Advances in Computing Research, Orlando, United States of America, 8th - 10th May, 2023 |
Source of Publication: | ACR 2023: Proceedings of the 2023 International Conference on Advances in Computing Research, p. 214-224 |
Publisher: | Springer |
Place of Publication: | Cham, Switzerland |
Fields of Research (FoR) 2020: | 460208 Natural language processing |
Socio-Economic Objective (SEO) 2020: | 280115 Expanding knowledge in the information and computing sciences |
Peer Reviewed: | Yes |
HERDC Category Description: | E1 Refereed Scholarly Conference Publication |
Series Name: | Lecture Notes in Networks and Systems |
Series Number : | 700 |
Description: | Presented by Fahim Chowdhury |
Appears in Collections: | Conference Publication School of Health School of Science and Technology |
Files in This Item:
File | Size | Format |
---|
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.