@inproceedings{zhang-etal-2024-correcting,
title = "Correcting Pronoun Homophones with Subtle Semantics in {C}hinese Speech Recognition",
author = "Zhang, Zhaobo and
Gan, Rui and
Yuan, Pingpeng and
Jin, Hai",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.360",
pages = "4047--4058",
abstract = "Speech recognition is becoming prevalent in daily life. However, due to the similar semantic context of the entities and the overlap of Chinese pronunciation, the pronoun homophone, especially {``}他/她/它 (he/she/it){''}, (their pronunciation is {``}T{\=a}{''}) is usually recognized incorrectly. It poses a challenge to automatically correct them during the post-processing of Chinese speech recognition. In this paper, we propose three models to address the common confusion issues in this domain, tailored to various application scenarios. We implement the language model, the LSTM model with semantic features, and the rule-based assisted Ngram model, enabling our models to adapt to a wide range of requirements, from high-precision to low-resource offline devices. The extensive experiments show that our models achieve the highest recognition rate for {``}T{\=a}{''} correction with improvements from 70{\%} in the popular voice input methods up to 90{\%}. Further ablation analysis underscores the effectiveness of our models in enhancing recognition accuracy. Therefore, our models improve the overall experience of Chinese speech recognition of {``}T{\=a}{''} and reduce the burden of manual transcription corrections.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-correcting">
<titleInfo>
<title>Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaobo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Gan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pingpeng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech recognition is becoming prevalent in daily life. However, due to the similar semantic context of the entities and the overlap of Chinese pronunciation, the pronoun homophone, especially “他/她/它 (he/she/it)”, (their pronunciation is “Tā”) is usually recognized incorrectly. It poses a challenge to automatically correct them during the post-processing of Chinese speech recognition. In this paper, we propose three models to address the common confusion issues in this domain, tailored to various application scenarios. We implement the language model, the LSTM model with semantic features, and the rule-based assisted Ngram model, enabling our models to adapt to a wide range of requirements, from high-precision to low-resource offline devices. The extensive experiments show that our models achieve the highest recognition rate for “Tā” correction with improvements from 70% in the popular voice input methods up to 90%. Further ablation analysis underscores the effectiveness of our models in enhancing recognition accuracy. Therefore, our models improve the overall experience of Chinese speech recognition of “Tā” and reduce the burden of manual transcription corrections.</abstract>
<identifier type="citekey">zhang-etal-2024-correcting</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.360</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4047</start>
<end>4058</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition
%A Zhang, Zhaobo
%A Gan, Rui
%A Yuan, Pingpeng
%A Jin, Hai
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhang-etal-2024-correcting
%X Speech recognition is becoming prevalent in daily life. However, due to the similar semantic context of the entities and the overlap of Chinese pronunciation, the pronoun homophone, especially “他/她/它 (he/she/it)”, (their pronunciation is “Tā”) is usually recognized incorrectly. It poses a challenge to automatically correct them during the post-processing of Chinese speech recognition. In this paper, we propose three models to address the common confusion issues in this domain, tailored to various application scenarios. We implement the language model, the LSTM model with semantic features, and the rule-based assisted Ngram model, enabling our models to adapt to a wide range of requirements, from high-precision to low-resource offline devices. The extensive experiments show that our models achieve the highest recognition rate for “Tā” correction with improvements from 70% in the popular voice input methods up to 90%. Further ablation analysis underscores the effectiveness of our models in enhancing recognition accuracy. Therefore, our models improve the overall experience of Chinese speech recognition of “Tā” and reduce the burden of manual transcription corrections.
%U https://aclanthology.org/2024.lrec-main.360
%P 4047-4058
Markdown (Informal)
[Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition](https://aclanthology.org/2024.lrec-main.360) (Zhang et al., LREC-COLING 2024)
ACL