@inproceedings{zhang-etal-2022-mian,
title = "面向 Transformer 模型的蒙古语语音识别词特征编码方法(Researching of the {M}ongolian word encoding method based on Transformer {M}ongolian speech recognition)",
author = "Zhang, Xiaoxu and
Ma, Zhiqiang and
Liu, Zhiqiang and
Bao, Caijilahu",
editor = "Sun, Maosong and
Liu, Yang and
Che, Wanxiang and
Feng, Yang and
Qiu, Xipeng and
Rao, Gaoqi and
Chen, Yubo",
booktitle = "Proceedings of the 21st Chinese National Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Nanchang, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2022.ccl-1.30",
pages = "333--343",
abstract = "{``}针对 Transformer 模型在蒙古语语音识别任务中无法学习到带有控制符的蒙古语词和语音之间的对应关系,造成模型对蒙古语的不适应问题。提出一种面向 Transformer 模型的蒙古语词编码方法,方法使用蒙古语字母特征与词特征进行混合编码,通过结合蒙古语字母信息使 Transformer 模型能够区分带有控制符的蒙古语词,学习到蒙古语词与语音之间的对应关系。在 IMUT-MC 数据集上,构建 Transformer 模型并进行了词特征编码方法的消融实验和对比实验。消融实验结果表明,词特征编码方法在 HWER、WER、SER 上分别降低了 23.4{\%}、6.9{\%}、2.6{\%};对比实验结果表明,词特征编码方法领先于所有方法,HWER 和 WER 分别达到 11.8{\%}、19.8{\%}。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-mian">
<titleInfo>
<title>面向 Transformer 模型的蒙古语语音识别词特征编码方法(Researching of the Mongolian word encoding method based on Transformer Mongolian speech recognition)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoxu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caijilahu</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">Chinese</languageTerm>
<languageTerm type="code" authority="iso639-2b">chi</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Nanchang, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“针对 Transformer 模型在蒙古语语音识别任务中无法学习到带有控制符的蒙古语词和语音之间的对应关系,造成模型对蒙古语的不适应问题。提出一种面向 Transformer 模型的蒙古语词编码方法,方法使用蒙古语字母特征与词特征进行混合编码,通过结合蒙古语字母信息使 Transformer 模型能够区分带有控制符的蒙古语词,学习到蒙古语词与语音之间的对应关系。在 IMUT-MC 数据集上,构建 Transformer 模型并进行了词特征编码方法的消融实验和对比实验。消融实验结果表明,词特征编码方法在 HWER、WER、SER 上分别降低了 23.4%、6.9%、2.6%;对比实验结果表明,词特征编码方法领先于所有方法,HWER 和 WER 分别达到 11.8%、19.8%。”</abstract>
<identifier type="citekey">zhang-etal-2022-mian</identifier>
<location>
<url>https://aclanthology.org/2022.ccl-1.30</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>333</start>
<end>343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 面向 Transformer 模型的蒙古语语音识别词特征编码方法(Researching of the Mongolian word encoding method based on Transformer Mongolian speech recognition)
%A Zhang, Xiaoxu
%A Ma, Zhiqiang
%A Liu, Zhiqiang
%A Bao, Caijilahu
%Y Sun, Maosong
%Y Liu, Yang
%Y Che, Wanxiang
%Y Feng, Yang
%Y Qiu, Xipeng
%Y Rao, Gaoqi
%Y Chen, Yubo
%S Proceedings of the 21st Chinese National Conference on Computational Linguistics
%D 2022
%8 October
%I Chinese Information Processing Society of China
%C Nanchang, China
%G Chinese
%F zhang-etal-2022-mian
%X “针对 Transformer 模型在蒙古语语音识别任务中无法学习到带有控制符的蒙古语词和语音之间的对应关系,造成模型对蒙古语的不适应问题。提出一种面向 Transformer 模型的蒙古语词编码方法,方法使用蒙古语字母特征与词特征进行混合编码,通过结合蒙古语字母信息使 Transformer 模型能够区分带有控制符的蒙古语词,学习到蒙古语词与语音之间的对应关系。在 IMUT-MC 数据集上,构建 Transformer 模型并进行了词特征编码方法的消融实验和对比实验。消融实验结果表明,词特征编码方法在 HWER、WER、SER 上分别降低了 23.4%、6.9%、2.6%;对比实验结果表明,词特征编码方法领先于所有方法,HWER 和 WER 分别达到 11.8%、19.8%。”
%U https://aclanthology.org/2022.ccl-1.30
%P 333-343
Markdown (Informal)
[面向 Transformer 模型的蒙古语语音识别词特征编码方法(Researching of the Mongolian word encoding method based on Transformer Mongolian speech recognition)](https://aclanthology.org/2022.ccl-1.30) (Zhang et al., CCL 2022)
ACL