@inproceedings{ding-etal-2025-speech,
title = "Speech-Driven Editing System for {C}hinese {ASR} Errors",
author = "Ding, Sji-Jie and
Chang, Chia-Hui and
Jian, Zi-Xuan",
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.29/",
pages = "277--285",
ISBN = "979-8-89176-379-1",
abstract = "Despite recent advances in AI, ASR systems still struggle with real-world errors from pronunciation and homophones. To solve this issue, we propose a verbal-command-based correction system that enables users to utter natural-language instructions to refine recognition outputs with minimal effort. The system consists of three modules: an input classifier, a command classifier, and a correction labeler. To support training and evaluation, we simulate ASR errors via TTS and ASR pipelines to simulate the potential errors, followed by verbal correction commands issued based on linguistic features or LLMs. Experiments show that the overall system achieves over 80{\%} correction accuracy and delivers stable performance. Compared to manual correction, this system also demonstrates highly competitive correction speed, which sufficiently indicates its feasibility for practical deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2025-speech">
<titleInfo>
<title>Speech-Driven Editing System for Chinese ASR Errors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sji-Jie</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zi-Xuan</namePart>
<namePart type="family">Jian</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>Despite recent advances in AI, ASR systems still struggle with real-world errors from pronunciation and homophones. To solve this issue, we propose a verbal-command-based correction system that enables users to utter natural-language instructions to refine recognition outputs with minimal effort. The system consists of three modules: an input classifier, a command classifier, and a correction labeler. To support training and evaluation, we simulate ASR errors via TTS and ASR pipelines to simulate the potential errors, followed by verbal correction commands issued based on linguistic features or LLMs. Experiments show that the overall system achieves over 80% correction accuracy and delivers stable performance. Compared to manual correction, this system also demonstrates highly competitive correction speed, which sufficiently indicates its feasibility for practical deployment.</abstract>
<identifier type="citekey">ding-etal-2025-speech</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.29/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>277</start>
<end>285</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech-Driven Editing System for Chinese ASR Errors
%A Ding, Sji-Jie
%A Chang, Chia-Hui
%A Jian, Zi-Xuan
%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 ding-etal-2025-speech
%X Despite recent advances in AI, ASR systems still struggle with real-world errors from pronunciation and homophones. To solve this issue, we propose a verbal-command-based correction system that enables users to utter natural-language instructions to refine recognition outputs with minimal effort. The system consists of three modules: an input classifier, a command classifier, and a correction labeler. To support training and evaluation, we simulate ASR errors via TTS and ASR pipelines to simulate the potential errors, followed by verbal correction commands issued based on linguistic features or LLMs. Experiments show that the overall system achieves over 80% correction accuracy and delivers stable performance. Compared to manual correction, this system also demonstrates highly competitive correction speed, which sufficiently indicates its feasibility for practical deployment.
%U https://aclanthology.org/2025.rocling-main.29/
%P 277-285
Markdown (Informal)
[Speech-Driven Editing System for Chinese ASR Errors](https://aclanthology.org/2025.rocling-main.29/) (Ding et al., ROCLING 2025)
ACL
- Sji-Jie Ding, Chia-Hui Chang, and Zi-Xuan Jian. 2025. Speech-Driven Editing System for Chinese ASR Errors. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 277–285, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.