@inproceedings{chen-etal-2022-investigation,
title = "Investigation of feature processing modules and attention mechanisms in speaker verification system",
author = "Chen, Ting-Wei and
Lin, Wei-Ting and
Chen, Chia-Ping and
Lu, Chung-Li and
Chan, Bo-Cheng and
Cheng, Yu-Han and
Chuang, Hsiang-Feng and
Chen, Wei-Yu",
editor = "Chang, Yung-Chun and
Huang, Yi-Chin",
booktitle = "Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)",
month = nov,
year = "2022",
address = "Taipei, Taiwan",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
url = "https://aclanthology.org/2022.rocling-1.11/",
pages = "84--91",
language = "zho",
abstract = "In this paper, we use several combinations of feature front-end modules and attention mechanisms to improve the performance of our speaker verification system. An updated version of ECAPA-TDNN is chosen as a baseline. We replace and integrate different feature front-end and attention mechanism modules to compare and find the most effective model design, and this model would be our final system. We use VoxCeleb 2 dataset as our training set, and test the performance of our models on several test sets. With our final proposed model, we improved performance by 16{\%} over baseline on VoxSRC2022 valudation set, achieving better results for our speaker verification system."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-investigation">
<titleInfo>
<title>Investigation of feature processing modules and attention mechanisms in speaker verification system</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ting-Wei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Ting</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Ping</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Li</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo-Cheng</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Han</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsiang-Feng</namePart>
<namePart type="family">Chuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Yu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">zho</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yung-Chun</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Chin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we use several combinations of feature front-end modules and attention mechanisms to improve the performance of our speaker verification system. An updated version of ECAPA-TDNN is chosen as a baseline. We replace and integrate different feature front-end and attention mechanism modules to compare and find the most effective model design, and this model would be our final system. We use VoxCeleb 2 dataset as our training set, and test the performance of our models on several test sets. With our final proposed model, we improved performance by 16% over baseline on VoxSRC2022 valudation set, achieving better results for our speaker verification system.</abstract>
<identifier type="citekey">chen-etal-2022-investigation</identifier>
<location>
<url>https://aclanthology.org/2022.rocling-1.11/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>84</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigation of feature processing modules and attention mechanisms in speaker verification system
%A Chen, Ting-Wei
%A Lin, Wei-Ting
%A Chen, Chia-Ping
%A Lu, Chung-Li
%A Chan, Bo-Cheng
%A Cheng, Yu-Han
%A Chuang, Hsiang-Feng
%A Chen, Wei-Yu
%Y Chang, Yung-Chun
%Y Huang, Yi-Chin
%S Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)
%D 2022
%8 November
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taipei, Taiwan
%G zho
%F chen-etal-2022-investigation
%X In this paper, we use several combinations of feature front-end modules and attention mechanisms to improve the performance of our speaker verification system. An updated version of ECAPA-TDNN is chosen as a baseline. We replace and integrate different feature front-end and attention mechanism modules to compare and find the most effective model design, and this model would be our final system. We use VoxCeleb 2 dataset as our training set, and test the performance of our models on several test sets. With our final proposed model, we improved performance by 16% over baseline on VoxSRC2022 valudation set, achieving better results for our speaker verification system.
%U https://aclanthology.org/2022.rocling-1.11/
%P 84-91
Markdown (Informal)
[Investigation of feature processing modules and attention mechanisms in speaker verification system](https://aclanthology.org/2022.rocling-1.11/) (Chen et al., ROCLING 2022)
ACL
- Ting-Wei Chen, Wei-Ting Lin, Chia-Ping Chen, Chung-Li Lu, Bo-Cheng Chan, Yu-Han Cheng, Hsiang-Feng Chuang, and Wei-Yu Chen. 2022. Investigation of feature processing modules and attention mechanisms in speaker verification system. In Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022), pages 84–91, Taipei, Taiwan. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).