@inproceedings{huang-etal-2021-multi,
title = "Multi-accent Speech Separation with One Shot Learning",
author = "Huang, Kuan Po and
Wu, Yuan-Kuei and
Lee, Hung-yi",
editor = "Lee, Hung-Yi and
Mohtarami, Mitra and
Li, Shang-Wen and
Jin, Di and
Korpusik, Mandy and
Dong, Shuyan and
Vu, Ngoc Thang and
Hakkani-Tur, Dilek",
booktitle = "Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.metanlp-1.7",
doi = "10.18653/v1/2021.metanlp-1.7",
pages = "59--66",
abstract = "Speech separation is a problem in the field of speech processing that has been studied in full swing recently. However, there has not been much work studying a multi-accent speech separation scenario. Unseen speakers with new accents and noise aroused the domain mismatch problem which cannot be easily solved by conventional joint training methods. Thus, we applied MAML and FOMAML to tackle this problem and obtained higher average Si-SNRi values than joint training on almost all the unseen accents. This proved that these two methods do have the ability to generate well-trained parameters for adapting to speech mixtures of new speakers and accents. Furthermore, we found out that FOMAML obtains similar performance compared to MAML while saving a lot of time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2021-multi">
<titleInfo>
<title>Multi-accent Speech Separation with One Shot Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kuan</namePart>
<namePart type="given">Po</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan-Kuei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitra</namePart>
<namePart type="family">Mohtarami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shang-Wen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mandy</namePart>
<namePart type="family">Korpusik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyan</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech separation is a problem in the field of speech processing that has been studied in full swing recently. However, there has not been much work studying a multi-accent speech separation scenario. Unseen speakers with new accents and noise aroused the domain mismatch problem which cannot be easily solved by conventional joint training methods. Thus, we applied MAML and FOMAML to tackle this problem and obtained higher average Si-SNRi values than joint training on almost all the unseen accents. This proved that these two methods do have the ability to generate well-trained parameters for adapting to speech mixtures of new speakers and accents. Furthermore, we found out that FOMAML obtains similar performance compared to MAML while saving a lot of time.</abstract>
<identifier type="citekey">huang-etal-2021-multi</identifier>
<identifier type="doi">10.18653/v1/2021.metanlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.metanlp-1.7</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>59</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-accent Speech Separation with One Shot Learning
%A Huang, Kuan Po
%A Wu, Yuan-Kuei
%A Lee, Hung-yi
%Y Lee, Hung-Yi
%Y Mohtarami, Mitra
%Y Li, Shang-Wen
%Y Jin, Di
%Y Korpusik, Mandy
%Y Dong, Shuyan
%Y Vu, Ngoc Thang
%Y Hakkani-Tur, Dilek
%S Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F huang-etal-2021-multi
%X Speech separation is a problem in the field of speech processing that has been studied in full swing recently. However, there has not been much work studying a multi-accent speech separation scenario. Unseen speakers with new accents and noise aroused the domain mismatch problem which cannot be easily solved by conventional joint training methods. Thus, we applied MAML and FOMAML to tackle this problem and obtained higher average Si-SNRi values than joint training on almost all the unseen accents. This proved that these two methods do have the ability to generate well-trained parameters for adapting to speech mixtures of new speakers and accents. Furthermore, we found out that FOMAML obtains similar performance compared to MAML while saving a lot of time.
%R 10.18653/v1/2021.metanlp-1.7
%U https://aclanthology.org/2021.metanlp-1.7
%U https://doi.org/10.18653/v1/2021.metanlp-1.7
%P 59-66
Markdown (Informal)
[Multi-accent Speech Separation with One Shot Learning](https://aclanthology.org/2021.metanlp-1.7) (Huang et al., MetaNLP 2021)
ACL
- Kuan Po Huang, Yuan-Kuei Wu, and Hung-yi Lee. 2021. Multi-accent Speech Separation with One Shot Learning. In Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing, pages 59–66, Online. Association for Computational Linguistics.