@inproceedings{liao-etal-2025-taiwanese,
title = "{T}aiwanese {H}akka Across {T}aiwan Corpus and {F}ormosa Speech Recognition Challenge 2025 {--} Dapu {\&} Zhao{'}an Accents",
author = "Liao, Yuan-Fu and
Kuo, Chih-Chung and
Huang, Chao-Shih and
Lan, Yu-Siang and
Lai, Han-Chun and
Hsu, Wen-Han",
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.48/",
pages = "427--434",
ISBN = "979-8-89176-379-1",
abstract = "To revive the endangered Hakka language in Taiwan, the first large-scale Hakka speech corpus covering all aspects of Taiwanese Hakka across Taiwan (HAT) was created. This paper introduces the second part of the HAT corpus: the Dapu and Zhao{'}an accents. Furthermore, to promote this newly constructed corpus and evaluate the performance of the most advanced Hakka ASR system, the 2025 Formosa Speech Recognition Challenge, FSR-2025{--}Hakka ASR II, was held. Sixteen teams participated on two tracks: speech-to-Hakka-Hanzi and speech-to Hakka-Pinyin. The best results were: Hanzi character error rate (CER) 7.50{\%}; Pinyin syllable error rate (SER) 14.81{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liao-etal-2025-taiwanese">
<titleInfo>
<title>Taiwanese Hakka Across Taiwan Corpus and Formosa Speech Recognition Challenge 2025 – Dapu & Zhao’an Accents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan-Fu</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chih-Chung</namePart>
<namePart type="family">Kuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Shih</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Siang</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han-Chun</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Han</namePart>
<namePart type="family">Hsu</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>To revive the endangered Hakka language in Taiwan, the first large-scale Hakka speech corpus covering all aspects of Taiwanese Hakka across Taiwan (HAT) was created. This paper introduces the second part of the HAT corpus: the Dapu and Zhao’an accents. Furthermore, to promote this newly constructed corpus and evaluate the performance of the most advanced Hakka ASR system, the 2025 Formosa Speech Recognition Challenge, FSR-2025–Hakka ASR II, was held. Sixteen teams participated on two tracks: speech-to-Hakka-Hanzi and speech-to Hakka-Pinyin. The best results were: Hanzi character error rate (CER) 7.50%; Pinyin syllable error rate (SER) 14.81%.</abstract>
<identifier type="citekey">liao-etal-2025-taiwanese</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.48/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>427</start>
<end>434</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Taiwanese Hakka Across Taiwan Corpus and Formosa Speech Recognition Challenge 2025 – Dapu & Zhao’an Accents
%A Liao, Yuan-Fu
%A Kuo, Chih-Chung
%A Huang, Chao-Shih
%A Lan, Yu-Siang
%A Lai, Han-Chun
%A Hsu, Wen-Han
%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 liao-etal-2025-taiwanese
%X To revive the endangered Hakka language in Taiwan, the first large-scale Hakka speech corpus covering all aspects of Taiwanese Hakka across Taiwan (HAT) was created. This paper introduces the second part of the HAT corpus: the Dapu and Zhao’an accents. Furthermore, to promote this newly constructed corpus and evaluate the performance of the most advanced Hakka ASR system, the 2025 Formosa Speech Recognition Challenge, FSR-2025–Hakka ASR II, was held. Sixteen teams participated on two tracks: speech-to-Hakka-Hanzi and speech-to Hakka-Pinyin. The best results were: Hanzi character error rate (CER) 7.50%; Pinyin syllable error rate (SER) 14.81%.
%U https://aclanthology.org/2025.rocling-main.48/
%P 427-434
Markdown (Informal)
[Taiwanese Hakka Across Taiwan Corpus and Formosa Speech Recognition Challenge 2025 – Dapu & Zhao’an Accents](https://aclanthology.org/2025.rocling-main.48/) (Liao et al., ROCLING 2025)
ACL