Towards End-to-End Speech Recognition System for Pashto Language Using Transformer Model

Munaza Sher ()
Additional contact information
Munaza Sher: University of Engineering and Technology

International Journal of Innovations in Science & Technology, 2024, vol. 6, issue 1, 115-131

Abstract: The conventional use of Hidden Markov Models (HMMs), and Gaussian Mixture Models (GMMs)for speech recognition posed setup challenges and inefficiency. This paper adopts the Transformer model for Pashto continuous speech recognition, offering an End-to-End (E2E) system that directly represents acoustic signals in the label sequence, simplifying implementation. This study introduces a Transformer model leveraging its state-of-the-art capabilities, including parallelization and self-attention mechanisms. With limited data for Pashto, the Transformer is chosen for its proficiency in handling constraints. The objective is to develop an accurate Pashto speech recognition system. Through 200 hours of conversational data, the study achieves a Word Error Rate (WER) of up to 51% and a Character Error Rate (CER) of up to 29%. The model's parameters are fine-tuned, and the dataset size increased, leading to significant improvements. Results demonstrate the Transformer's effectiveness, showcasing its prowess in limited data scenarios. The study attains notable WER and CER metrics, affirming the model's ability to recognize Pashto speech accurately. In conclusion, the study establishes the Transformer as a robust choice for Pashto speech recognition, emphasizing its adaptability to limited data conditions. It fills a gap in ASR research for the Pashto language, contributing to the advancement of speech recognition technology in under-resourced languages. The study highlights the potential for further improvement with increased training data. The findings underscore the importance of fine-tuning and dataset augmentation in enhancing model performance and reducing error rates.

Keywords: Hidden Markov Models (HMMs); Gaussian Mixture Models (GMMs); End-to-End (E2E); Character Error Rate (CER) (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journal.50sea.com/index.php/IJIST/article/view/659/1278 (application/pdf)
https://journal.50sea.com/index.php/IJIST/article/view/659 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:abq:ijist1:v:6:y:2024:i:1:p:115-131

Access Statistics for this article

International Journal of Innovations in Science & Technology is currently edited by Prof. Dr. Syed Amer Mahmood

More articles in International Journal of Innovations in Science & Technology from 50sea
Bibliographic data for series maintained by Iqra Nazeer ().