@inproceedings{he-chen-2025-leveraging,
title = "Leveraging Weak Segment Labels for Robust Automated Speaking Assessment in Read-Aloud Tasks",
author = "He, Yue-Yang 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.18/",
pages = "146--152",
ISBN = "979-8-89176-379-1",
abstract = "Automated speaking assessment (ASA) has become a crucial component in computer-assisted language learning, providing scalable, objective, and timely feedback to second-language learners. While early ASA systems relied on hand-crafted features and shallow classifiers, recent advances in self-supervised learning (SSL) have enabled richer representations for both text and speech, improving assessment accuracy. Despite these advances, challenges remain in evaluating long speech responses, due to limited labeled data, class imbalance, and the importance of pronunciation clarity and fluency, especially for read-aloud tasks. In this work, we propose a segment-based ASA framework leveraging WhisperX to split long responses into shorter fragments, generate weak labels from holistic scores, and aggregate segment-level predictions to obtain final proficiency scores. Experiments on the GEPT corpus demonstrate that our framework outperforms baseline holistic models, generalizes robustly to unseen prompts and speakers, and provides diagnostic insights at both segment and response levels."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-chen-2025-leveraging">
<titleInfo>
<title>Leveraging Weak Segment Labels for Robust Automated Speaking Assessment in Read-Aloud Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue-Yang</namePart>
<namePart type="family">He</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>Automated speaking assessment (ASA) has become a crucial component in computer-assisted language learning, providing scalable, objective, and timely feedback to second-language learners. While early ASA systems relied on hand-crafted features and shallow classifiers, recent advances in self-supervised learning (SSL) have enabled richer representations for both text and speech, improving assessment accuracy. Despite these advances, challenges remain in evaluating long speech responses, due to limited labeled data, class imbalance, and the importance of pronunciation clarity and fluency, especially for read-aloud tasks. In this work, we propose a segment-based ASA framework leveraging WhisperX to split long responses into shorter fragments, generate weak labels from holistic scores, and aggregate segment-level predictions to obtain final proficiency scores. Experiments on the GEPT corpus demonstrate that our framework outperforms baseline holistic models, generalizes robustly to unseen prompts and speakers, and provides diagnostic insights at both segment and response levels.</abstract>
<identifier type="citekey">he-chen-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.18/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>146</start>
<end>152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Weak Segment Labels for Robust Automated Speaking Assessment in Read-Aloud Tasks
%A He, Yue-Yang
%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 he-chen-2025-leveraging
%X Automated speaking assessment (ASA) has become a crucial component in computer-assisted language learning, providing scalable, objective, and timely feedback to second-language learners. While early ASA systems relied on hand-crafted features and shallow classifiers, recent advances in self-supervised learning (SSL) have enabled richer representations for both text and speech, improving assessment accuracy. Despite these advances, challenges remain in evaluating long speech responses, due to limited labeled data, class imbalance, and the importance of pronunciation clarity and fluency, especially for read-aloud tasks. In this work, we propose a segment-based ASA framework leveraging WhisperX to split long responses into shorter fragments, generate weak labels from holistic scores, and aggregate segment-level predictions to obtain final proficiency scores. Experiments on the GEPT corpus demonstrate that our framework outperforms baseline holistic models, generalizes robustly to unseen prompts and speakers, and provides diagnostic insights at both segment and response levels.
%U https://aclanthology.org/2025.rocling-main.18/
%P 146-152
Markdown (Informal)
[Leveraging Weak Segment Labels for Robust Automated Speaking Assessment in Read-Aloud Tasks](https://aclanthology.org/2025.rocling-main.18/) (He & Chen, ROCLING 2025)
ACL