One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Zhichao, Xie, Qicong, Li, Tao, Du, Hongqiang, Xie, Lei, Zhu, Pengcheng, Bi, Mengxiao
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Wang, Zhichao
Xie, Qicong
Li, Tao
Du, Hongqiang
Xie, Lei
Zhu, Pengcheng
Bi, Mengxiao
description One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one utterance from target speaker as training data. Finally, to comprehensively decouple the speech factors, i.e., content, speaker, style, and transfer source style to the target, a prosody module is used to extract prosody representation. Experiments show that our approach is superior to the state-of-the-art one-shot VC systems in terms of style and speaker similarity; additionally, our approach also maintains good speech quality.
doi_str_mv 10.48550/arxiv.2111.12277
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2111_12277</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2111_12277</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-74b06d9ab90f42891f811c0a8dac6e02377654091513fbd9ea4e2f82d3cc39023</originalsourceid><addsrcrecordid>eNotj81KxDAUhbNxIaMP4Mq8QGv-2iTLsTiOMNDFFLflNrnB4piUtAzO21tHVwfO-TjwEfLAWalMVbEnyN_juRSc85ILofUt2bcRi_kjLfQ9jQ5pk-IZ8zymSHcp0-NyOSHtMsQ5YKbPMKOnbaTHCeFzLbYepgWWFb8jNwFOM97_54Z0u5eu2ReH9vWt2R4KqLUutBpY7S0MlgUljOXBcO4YGA-uRiak1nWlmOUVl2HwFkGhCEZ46Zy0674hj3-3V5V-yuMX5Ev_q9RfleQPCyFFkQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation</title><source>arXiv.org</source><creator>Wang, Zhichao ; Xie, Qicong ; Li, Tao ; Du, Hongqiang ; Xie, Lei ; Zhu, Pengcheng ; Bi, Mengxiao</creator><creatorcontrib>Wang, Zhichao ; Xie, Qicong ; Li, Tao ; Du, Hongqiang ; Xie, Lei ; Zhu, Pengcheng ; Bi, Mengxiao</creatorcontrib><description>One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one utterance from target speaker as training data. Finally, to comprehensively decouple the speech factors, i.e., content, speaker, style, and transfer source style to the target, a prosody module is used to extract prosody representation. Experiments show that our approach is superior to the state-of-the-art one-shot VC systems in terms of style and speaker similarity; additionally, our approach also maintains good speech quality.</description><identifier>DOI: 10.48550/arxiv.2111.12277</identifier><language>eng</language><subject>Computer Science - Sound</subject><creationdate>2021-11</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2111.12277$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2111.12277$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Zhichao</creatorcontrib><creatorcontrib>Xie, Qicong</creatorcontrib><creatorcontrib>Li, Tao</creatorcontrib><creatorcontrib>Du, Hongqiang</creatorcontrib><creatorcontrib>Xie, Lei</creatorcontrib><creatorcontrib>Zhu, Pengcheng</creatorcontrib><creatorcontrib>Bi, Mengxiao</creatorcontrib><title>One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation</title><description>One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one utterance from target speaker as training data. Finally, to comprehensively decouple the speech factors, i.e., content, speaker, style, and transfer source style to the target, a prosody module is used to extract prosody representation. Experiments show that our approach is superior to the state-of-the-art one-shot VC systems in terms of style and speaker similarity; additionally, our approach also maintains good speech quality.</description><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81KxDAUhbNxIaMP4Mq8QGv-2iTLsTiOMNDFFLflNrnB4piUtAzO21tHVwfO-TjwEfLAWalMVbEnyN_juRSc85ILofUt2bcRi_kjLfQ9jQ5pk-IZ8zymSHcp0-NyOSHtMsQ5YKbPMKOnbaTHCeFzLbYepgWWFb8jNwFOM97_54Z0u5eu2ReH9vWt2R4KqLUutBpY7S0MlgUljOXBcO4YGA-uRiak1nWlmOUVl2HwFkGhCEZ46Zy0674hj3-3V5V-yuMX5Ev_q9RfleQPCyFFkQ</recordid><startdate>20211124</startdate><enddate>20211124</enddate><creator>Wang, Zhichao</creator><creator>Xie, Qicong</creator><creator>Li, Tao</creator><creator>Du, Hongqiang</creator><creator>Xie, Lei</creator><creator>Zhu, Pengcheng</creator><creator>Bi, Mengxiao</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20211124</creationdate><title>One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation</title><author>Wang, Zhichao ; Xie, Qicong ; Li, Tao ; Du, Hongqiang ; Xie, Lei ; Zhu, Pengcheng ; Bi, Mengxiao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-74b06d9ab90f42891f811c0a8dac6e02377654091513fbd9ea4e2f82d3cc39023</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Zhichao</creatorcontrib><creatorcontrib>Xie, Qicong</creatorcontrib><creatorcontrib>Li, Tao</creatorcontrib><creatorcontrib>Du, Hongqiang</creatorcontrib><creatorcontrib>Xie, Lei</creatorcontrib><creatorcontrib>Zhu, Pengcheng</creatorcontrib><creatorcontrib>Bi, Mengxiao</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wang, Zhichao</au><au>Xie, Qicong</au><au>Li, Tao</au><au>Du, Hongqiang</au><au>Xie, Lei</au><au>Zhu, Pengcheng</au><au>Bi, Mengxiao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation</atitle><date>2021-11-24</date><risdate>2021</risdate><abstract>One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one utterance from target speaker as training data. Finally, to comprehensively decouple the speech factors, i.e., content, speaker, style, and transfer source style to the target, a prosody module is used to extract prosody representation. Experiments show that our approach is superior to the state-of-the-art one-shot VC systems in terms of style and speaker similarity; additionally, our approach also maintains good speech quality.</abstract><doi>10.48550/arxiv.2111.12277</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2111.12277
ispartof
issn
language eng
recordid cdi_arxiv_primary_2111_12277
source arXiv.org
subjects Computer Science - Sound
title One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T17%3A53%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=One-shot%20Voice%20Conversion%20For%20Style%20Transfer%20Based%20On%20Speaker%20Adaptation&rft.au=Wang,%20Zhichao&rft.date=2021-11-24&rft_id=info:doi/10.48550/arxiv.2111.12277&rft_dat=%3Carxiv_GOX%3E2111_12277%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true