@inproceedings{lin-etal-2025-channel,
title = "A Channel-Aware Anomaly-Guided Data Augmentation Framework for the {FSR}-2025 {H}akka Speech Recognition Challenge",
author = "Lin, Siang-Ting and
Hao, Arthur and
Hua, Chiun-Yu and
Huang, Kuan-Tang and
Chen, Berlin",
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.60/",
pages = "499--503",
ISBN = "979-8-89176-379-1",
abstract = "The Formosa Speech Recognition Challenge 2025 (FSR-2025) focuses on Taiwanese Hakka, a low-resource language with limited data diversity and channel coverage. To address this challenge, we propose a channel-aware, data-centric framework that leverages multilingual foundation models to mitigate mismatches between field recordings and training data. Our method integrates unsupervised anomaly detection and channel-conditioned augmentation to enhance data representativeness before ASR fine-tuning, aiming to explore the potential for improving robustness in low-resource Hakka speech recognition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2025-channel">
<titleInfo>
<title>A Channel-Aware Anomaly-Guided Data Augmentation Framework for the FSR-2025 Hakka Speech Recognition Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siang-Ting</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiun-Yu</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan-Tang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berlin</namePart>
<namePart type="family">Chen</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>The Formosa Speech Recognition Challenge 2025 (FSR-2025) focuses on Taiwanese Hakka, a low-resource language with limited data diversity and channel coverage. To address this challenge, we propose a channel-aware, data-centric framework that leverages multilingual foundation models to mitigate mismatches between field recordings and training data. Our method integrates unsupervised anomaly detection and channel-conditioned augmentation to enhance data representativeness before ASR fine-tuning, aiming to explore the potential for improving robustness in low-resource Hakka speech recognition.</abstract>
<identifier type="citekey">lin-etal-2025-channel</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.60/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>499</start>
<end>503</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Channel-Aware Anomaly-Guided Data Augmentation Framework for the FSR-2025 Hakka Speech Recognition Challenge
%A Lin, Siang-Ting
%A Hao, Arthur
%A Hua, Chiun-Yu
%A Huang, Kuan-Tang
%A Chen, Berlin
%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 lin-etal-2025-channel
%X The Formosa Speech Recognition Challenge 2025 (FSR-2025) focuses on Taiwanese Hakka, a low-resource language with limited data diversity and channel coverage. To address this challenge, we propose a channel-aware, data-centric framework that leverages multilingual foundation models to mitigate mismatches between field recordings and training data. Our method integrates unsupervised anomaly detection and channel-conditioned augmentation to enhance data representativeness before ASR fine-tuning, aiming to explore the potential for improving robustness in low-resource Hakka speech recognition.
%U https://aclanthology.org/2025.rocling-main.60/
%P 499-503
Markdown (Informal)
[A Channel-Aware Anomaly-Guided Data Augmentation Framework for the FSR-2025 Hakka Speech Recognition Challenge](https://aclanthology.org/2025.rocling-main.60/) (Lin et al., ROCLING 2025)
ACL