@inproceedings{zhang-etal-2021-ji-yu-gai,
title = "基于改进{C}onformer的新闻领域端到端语音识别(End-to-End Speech Recognition in News Field based on Conformer)",
author = "Zhang, Jimin and
Zao, Kerekadeer and
Shen, Yunfei and
Ai, Shanwumaier and
Wang, Liejun",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.76",
pages = "851--861",
abstract = "目前,开源的中文语音识别数据集多为面向通用领域,缺少面向新闻领域的开源语音识别语料库,因此本文构建了面向新闻领域的中文语音识别数据集CHNEWSASR并使用ESPNET-0.9.6框架的RNN、Transformer和Conformer等模型对数据集的有效性进行了验证,实验表明本文所构建的语料在最好的模型上CER为4.8{\%},SER为39.4{\%}。由于新闻联播主持人说话语速相对较快,本文构建的数据集文本平均长度为28个字符是Aishell1数据集文本平均长度的2倍,且以往的研究中训练目标函数通常为基于字或词水平,缺乏明确的句子水平关系,因此本文提出了一个句子层级的一致性模块与Conformer模型结合直接减少源语音和目标文本的表示差异,在开源的Aishell1数据集上其CER降低0.4{\%},SER降低2{\%};在CHNEWSASR数据集上其CER降低0.9{\%},SER降低3{\%},实验结果表明该方法不提升模型参数量的前提下能有效提升语音识别的质量。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2021-ji-yu-gai">
<titleInfo>
<title>基于改进Conformer的新闻领域端到端语音识别(End-to-End Speech Recognition in News Field based on Conformer)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kerekadeer</namePart>
<namePart type="family">Zao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunfei</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanwumaier</namePart>
<namePart type="family">Ai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liejun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</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 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</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">Shizhu</namePart>
<namePart type="family">He</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>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>目前,开源的中文语音识别数据集多为面向通用领域,缺少面向新闻领域的开源语音识别语料库,因此本文构建了面向新闻领域的中文语音识别数据集CHNEWSASR并使用ESPNET-0.9.6框架的RNN、Transformer和Conformer等模型对数据集的有效性进行了验证,实验表明本文所构建的语料在最好的模型上CER为4.8%,SER为39.4%。由于新闻联播主持人说话语速相对较快,本文构建的数据集文本平均长度为28个字符是Aishell1数据集文本平均长度的2倍,且以往的研究中训练目标函数通常为基于字或词水平,缺乏明确的句子水平关系,因此本文提出了一个句子层级的一致性模块与Conformer模型结合直接减少源语音和目标文本的表示差异,在开源的Aishell1数据集上其CER降低0.4%,SER降低2%;在CHNEWSASR数据集上其CER降低0.9%,SER降低3%,实验结果表明该方法不提升模型参数量的前提下能有效提升语音识别的质量。</abstract>
<identifier type="citekey">zhang-etal-2021-ji-yu-gai</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.76</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>851</start>
<end>861</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于改进Conformer的新闻领域端到端语音识别(End-to-End Speech Recognition in News Field based on Conformer)
%A Zhang, Jimin
%A Zao, Kerekadeer
%A Shen, Yunfei
%A Ai, Shanwumaier
%A Wang, Liejun
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G Chinese
%F zhang-etal-2021-ji-yu-gai
%X 目前,开源的中文语音识别数据集多为面向通用领域,缺少面向新闻领域的开源语音识别语料库,因此本文构建了面向新闻领域的中文语音识别数据集CHNEWSASR并使用ESPNET-0.9.6框架的RNN、Transformer和Conformer等模型对数据集的有效性进行了验证,实验表明本文所构建的语料在最好的模型上CER为4.8%,SER为39.4%。由于新闻联播主持人说话语速相对较快,本文构建的数据集文本平均长度为28个字符是Aishell1数据集文本平均长度的2倍,且以往的研究中训练目标函数通常为基于字或词水平,缺乏明确的句子水平关系,因此本文提出了一个句子层级的一致性模块与Conformer模型结合直接减少源语音和目标文本的表示差异,在开源的Aishell1数据集上其CER降低0.4%,SER降低2%;在CHNEWSASR数据集上其CER降低0.9%,SER降低3%,实验结果表明该方法不提升模型参数量的前提下能有效提升语音识别的质量。
%U https://aclanthology.org/2021.ccl-1.76
%P 851-861
Markdown (Informal)
[基于改进Conformer的新闻领域端到端语音识别(End-to-End Speech Recognition in News Field based on Conformer)](https://aclanthology.org/2021.ccl-1.76) (Zhang et al., CCL 2021)
ACL