@inproceedings{chen-etal-2025-whisper,
title = "A Whisper-Based System with Multi-Faceted Data Augmentation for Low-Resource Language",
author = "Chen, Pin-Cheng and
Chen, Yu-Chi and
Liang, Chia-Chun and
Lin, Cheng-Yu and
Tsai, Ping-Juei and
Ma, Wei-Yun",
editor = "Chang, Kai-Wei and
Lu, Ke-Han and
Yang, Chih-Kai and
Tam, Zhi-Rui and
Chang, Wen-Yu and
Wang, Chung-Che",
booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
month = nov,
year = "2025",
address = "National Taiwan University, Taipei City, Taiwan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.rocling-main.59/",
pages = "489--498",
ISBN = "979-8-89176-379-1",
abstract = "This paper presents a comprehensive approach for the Formosa Speech Recognition Challenge 2025 (FSR-2025), targeting automatic speech recognition (ASR) for the under-resourced Dapu and Zhao{'}an dialects of Taiwanese Hakka. Our method integrates data augmentation and robustness techniques, including SpecAugment, dialect-aware special tokens, text-to-speech (TTS) augmentation, noise/reverberation mixing, and speed perturbation, to mitigate data scarcity and domain mismatch. Experiments on the official FSR-2025 datasets show consistent improvements in both character error rate (CER) and word error rate (WER). Extensive ablation studies further confirm that each component contributes positively. These results offer a practical path toward robust ASR for under-resourced Hakka dialects and suggest broader applicability to other low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-whisper">
<titleInfo>
<title>A Whisper-Based System with Multi-Faceted Data Augmentation for Low-Resource Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pin-Cheng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Chun</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng-Yu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping-Juei</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Yun</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke-Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chih-Kai</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi-Rui</namePart>
<namePart type="family">Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Yu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Che</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">National Taiwan University, Taipei City, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-379-1</identifier>
</relatedItem>
<abstract>This paper presents a comprehensive approach for the Formosa Speech Recognition Challenge 2025 (FSR-2025), targeting automatic speech recognition (ASR) for the under-resourced Dapu and Zhao’an dialects of Taiwanese Hakka. Our method integrates data augmentation and robustness techniques, including SpecAugment, dialect-aware special tokens, text-to-speech (TTS) augmentation, noise/reverberation mixing, and speed perturbation, to mitigate data scarcity and domain mismatch. Experiments on the official FSR-2025 datasets show consistent improvements in both character error rate (CER) and word error rate (WER). Extensive ablation studies further confirm that each component contributes positively. These results offer a practical path toward robust ASR for under-resourced Hakka dialects and suggest broader applicability to other low-resource languages.</abstract>
<identifier type="citekey">chen-etal-2025-whisper</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.59/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>489</start>
<end>498</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Whisper-Based System with Multi-Faceted Data Augmentation for Low-Resource Language
%A Chen, Pin-Cheng
%A Chen, Yu-Chi
%A Liang, Chia-Chun
%A Lin, Cheng-Yu
%A Tsai, Ping-Juei
%A Ma, Wei-Yun
%Y Chang, Kai-Wei
%Y Lu, Ke-Han
%Y Yang, Chih-Kai
%Y Tam, Zhi-Rui
%Y Chang, Wen-Yu
%Y Wang, Chung-Che
%S Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C National Taiwan University, Taipei City, Taiwan
%@ 979-8-89176-379-1
%F chen-etal-2025-whisper
%X This paper presents a comprehensive approach for the Formosa Speech Recognition Challenge 2025 (FSR-2025), targeting automatic speech recognition (ASR) for the under-resourced Dapu and Zhao’an dialects of Taiwanese Hakka. Our method integrates data augmentation and robustness techniques, including SpecAugment, dialect-aware special tokens, text-to-speech (TTS) augmentation, noise/reverberation mixing, and speed perturbation, to mitigate data scarcity and domain mismatch. Experiments on the official FSR-2025 datasets show consistent improvements in both character error rate (CER) and word error rate (WER). Extensive ablation studies further confirm that each component contributes positively. These results offer a practical path toward robust ASR for under-resourced Hakka dialects and suggest broader applicability to other low-resource languages.
%U https://aclanthology.org/2025.rocling-main.59/
%P 489-498
Markdown (Informal)
[A Whisper-Based System with Multi-Faceted Data Augmentation for Low-Resource Language](https://aclanthology.org/2025.rocling-main.59/) (Chen et al., ROCLING 2025)
ACL