@inproceedings{b602c464d5c34e44aec3ad554633f9b0,
title = "Enhancing Automatic Speech Recognition Performance Through Multi-Speaker Text-to-Speech",
abstract = "In this study, we present a novel approach to enhancing the performance of our Hakka Automatic Speech Recognition (ASR) model through the strategic use of Text-to-Speech (TTS) amplification techniques. Our investigation explores the integration of diverse speakers to expand our training dataset, leading to a notable reduction of Character Error Rate (CER) approximately 0.2 in the validation set and approximately 3.96 on the test set. These compelling results affirm the effectiveness of multi-speaker TTS strategies in generating ASR data, ultimately bolstering the resilience and precision of our ASR system.",
keywords = "Automatic Speech Recognition, Data extension, Multi-Speaker Text-to-Speech",
author = "Chen, {Po Kai} and Wang, {Hsin Min} and Huang, {Bing Jhih} and Chen, {Chi Tao} and Wang, {Jia Ching}",
note = "Publisher Copyright: {\textcopyright} 2023 ROCLING 2023 - Proceedings of the 35th Conference on Computational Linguistics and Speech Processing. All rights reserved.; 35th Conference on Computational Linguistics and Speech Processing, ROCLING 2023 ; Conference date: 20-10-2023 Through 21-10-2023",
year = "2023",
language = "???core.languages.en_GB???",
series = "ROCLING 2023 - Proceedings of the 35th Conference on Computational Linguistics and Speech Processing",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
pages = "370--375",
editor = "Jheng-Long Wu and Ming-Hsiang Su and Hen-Hsen Huang and Yu Tsao and Hou-Chiang Tseng and Chia-Hui Chang and Lung-Hao Lee and Yuan-Fu Liao and Wei-Yun Ma",
booktitle = "ROCLING 2023 - Proceedings of the 35th Conference on Computational Linguistics and Speech Processing",
}