@inproceedings{zhu-etal-2022-ji,
title = "基于注意力的蒙古语说话人特征提取方法(Attention based {M}ongolian Speaker Feature Extraction)",
author = "Zhu, Fangyuan and
Ma, Zhiqiang and
Liu, Zhiqiang and
Bao, Caijilahu and
Wang, Hongbin",
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-1.31",
pages = "344--354",
abstract = "{``}说话人特征提取模型提取到的说话人特征之间区分性低,使得蒙古语声学模型无法学习到区分性信息,导致模型无法适应不同说话人。提出一种基于注意力的说话人自适应方法,方法引入神经图灵机进行自适应,增加记忆模块存放说话人特征,采用注意力机制计算记忆模块中说话人特征与当前语音说话人特征的相似权重矩阵,通过权重矩阵重新组合成说话人特征s-vector,进而提高说话人特征之间的区分性。在IMUT-MCT数据集上,进行说话人特征提取方法的消融实验、模型自适应实验和案例分析。实验结果表明,对比不同说话人特征s-vector、i-vector与d-vector,s-vector比其他两种方法的SER和WER分别降低4.96{\%}、1.08{\%};在不同的蒙古语声学模型上进行比较,提出的方法相对于基线均有性能提升。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2022-ji">
<titleInfo>
<title>基于注意力的蒙古语说话人特征提取方法(Attention based Mongolian Speaker Feature Extraction)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fangyuan</namePart>
<namePart type="family">Zhu</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>
<name type="personal">
<namePart type="given">Hongbin</namePart>
<namePart type="family">Wang</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>“说话人特征提取模型提取到的说话人特征之间区分性低,使得蒙古语声学模型无法学习到区分性信息,导致模型无法适应不同说话人。提出一种基于注意力的说话人自适应方法,方法引入神经图灵机进行自适应,增加记忆模块存放说话人特征,采用注意力机制计算记忆模块中说话人特征与当前语音说话人特征的相似权重矩阵,通过权重矩阵重新组合成说话人特征s-vector,进而提高说话人特征之间的区分性。在IMUT-MCT数据集上,进行说话人特征提取方法的消融实验、模型自适应实验和案例分析。实验结果表明,对比不同说话人特征s-vector、i-vector与d-vector,s-vector比其他两种方法的SER和WER分别降低4.96%、1.08%;在不同的蒙古语声学模型上进行比较,提出的方法相对于基线均有性能提升。”</abstract>
<identifier type="citekey">zhu-etal-2022-ji</identifier>
<location>
<url>https://aclanthology.org/2022.ccl-1.31</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>344</start>
<end>354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于注意力的蒙古语说话人特征提取方法(Attention based Mongolian Speaker Feature Extraction)
%A Zhu, Fangyuan
%A Ma, Zhiqiang
%A Liu, Zhiqiang
%A Bao, Caijilahu
%A Wang, Hongbin
%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 zhu-etal-2022-ji
%X “说话人特征提取模型提取到的说话人特征之间区分性低,使得蒙古语声学模型无法学习到区分性信息,导致模型无法适应不同说话人。提出一种基于注意力的说话人自适应方法,方法引入神经图灵机进行自适应,增加记忆模块存放说话人特征,采用注意力机制计算记忆模块中说话人特征与当前语音说话人特征的相似权重矩阵,通过权重矩阵重新组合成说话人特征s-vector,进而提高说话人特征之间的区分性。在IMUT-MCT数据集上,进行说话人特征提取方法的消融实验、模型自适应实验和案例分析。实验结果表明,对比不同说话人特征s-vector、i-vector与d-vector,s-vector比其他两种方法的SER和WER分别降低4.96%、1.08%;在不同的蒙古语声学模型上进行比较,提出的方法相对于基线均有性能提升。”
%U https://aclanthology.org/2022.ccl-1.31
%P 344-354
Markdown (Informal)
[基于注意力的蒙古语说话人特征提取方法(Attention based Mongolian Speaker Feature Extraction)](https://aclanthology.org/2022.ccl-1.31) (Zhu et al., CCL 2022)
ACL