@inproceedings{hung-etal-2025-exploring,
title = "Exploring Sentence Stress Detection using Whisper-based Speech Models",
author = "Hung, Ting-An and
Hsieh, Yu-Hsuan and
Lo, Tien-Hong and
Hsu, Yung-Chang 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.33/",
pages = "314--319",
ISBN = "979-8-89176-379-1",
abstract = "Sentence stress reflects the relative prominence of words within a sentence. It is fundamental to speech intelligibility and naturalness, and is particularly important in second language (L2) learning. Accurate stress production facilitates effective communication and reduces misinterpretation. In this work, we investigate sentence stress detection (SSD) using Whisper-based transformer speech models under diverse settings, including model scaling, backbone{--}decoder interactions, architectural and regularization enhancements, and embedding visualization for interpretability. Results show that smaller Whisper variants achieve stronger performance under limited data, while architectural and regularization enhancements improves stability and generalization. Embedding analysis reveal clear separation between stressed and unstressed words. These findings offer practical insights into model selection, architecture design, and interpretability for SSD applications, with implications for L2 learning support tools."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hung-etal-2025-exploring">
<titleInfo>
<title>Exploring Sentence Stress Detection using Whisper-based Speech Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting-An</namePart>
<namePart type="family">Hung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Hsuan</namePart>
<namePart type="family">Hsieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tien-Hong</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yung-Chang</namePart>
<namePart type="family">Hsu</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>Sentence stress reflects the relative prominence of words within a sentence. It is fundamental to speech intelligibility and naturalness, and is particularly important in second language (L2) learning. Accurate stress production facilitates effective communication and reduces misinterpretation. In this work, we investigate sentence stress detection (SSD) using Whisper-based transformer speech models under diverse settings, including model scaling, backbone–decoder interactions, architectural and regularization enhancements, and embedding visualization for interpretability. Results show that smaller Whisper variants achieve stronger performance under limited data, while architectural and regularization enhancements improves stability and generalization. Embedding analysis reveal clear separation between stressed and unstressed words. These findings offer practical insights into model selection, architecture design, and interpretability for SSD applications, with implications for L2 learning support tools.</abstract>
<identifier type="citekey">hung-etal-2025-exploring</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.33/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>314</start>
<end>319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Sentence Stress Detection using Whisper-based Speech Models
%A Hung, Ting-An
%A Hsieh, Yu-Hsuan
%A Lo, Tien-Hong
%A Hsu, Yung-Chang
%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 hung-etal-2025-exploring
%X Sentence stress reflects the relative prominence of words within a sentence. It is fundamental to speech intelligibility and naturalness, and is particularly important in second language (L2) learning. Accurate stress production facilitates effective communication and reduces misinterpretation. In this work, we investigate sentence stress detection (SSD) using Whisper-based transformer speech models under diverse settings, including model scaling, backbone–decoder interactions, architectural and regularization enhancements, and embedding visualization for interpretability. Results show that smaller Whisper variants achieve stronger performance under limited data, while architectural and regularization enhancements improves stability and generalization. Embedding analysis reveal clear separation between stressed and unstressed words. These findings offer practical insights into model selection, architecture design, and interpretability for SSD applications, with implications for L2 learning support tools.
%U https://aclanthology.org/2025.rocling-main.33/
%P 314-319
Markdown (Informal)
[Exploring Sentence Stress Detection using Whisper-based Speech Models](https://aclanthology.org/2025.rocling-main.33/) (Hung et al., ROCLING 2025)
ACL
- Ting-An Hung, Yu-Hsuan Hsieh, Tien-Hong Lo, Yung-Chang Hsu, and Berlin Chen. 2025. Exploring Sentence Stress Detection using Whisper-based Speech Models. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 314–319, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.