Speech Recognition for Indigenous Language Using Self-Supervised Learning and Natural Language Processing

Satoshi Tamura, Tomohiro Hattori, Yusuke Kato, Naoki Noguchi

2024

Abstract

This paper proposes a new concept to build a speech recognition system for an indigenous under-resourced language, by using another speech recognizer for a major language as well as neural machine translation and text autoencoder. Developing the recognizer for minor languages suffers from the lack of training speech data. Our method uses natural language processing techniques and text data, to compensate the lack of speech data. We focus on the model based on self-supervised learning, and utilize its sub-module as a feature extractor. We develop the recognizer sub-module for indigenous languages by making translation and autoencoder models. We conduct evaluation experiments for every systems and our paradigm. It is consequently found that our scheme can build the recognizer successfully, and improve the performance compared to the past works.

Paper Citation

in Harvard Style

Tamura S., Hattori T., Kato Y. and Noguchi N. (2024). Speech Recognition for Indigenous Language Using Self-Supervised Learning and Natural Language Processing. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 779-784. DOI: 10.5220/0012396300003654

in Bibtex Style

@conference{icpram24,
author={Satoshi Tamura and Tomohiro Hattori and Yusuke Kato and Naoki Noguchi},
title={Speech Recognition for Indigenous Language Using Self-Supervised Learning and Natural Language Processing},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={779-784},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012396300003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Speech Recognition for Indigenous Language Using Self-Supervised Learning and Natural Language Processing
SN - 978-989-758-684-2
AU - Tamura S.
AU - Hattori T.
AU - Kato Y.
AU - Noguchi N.
PY - 2024
SP - 779
EP - 784
DO - 10.5220/0012396300003654
PB - SciTePress