SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between converted speech and natural speech for voice conversion tasks. U...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2022-02 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Cheng-Hung, Hu Yu-Huai Peng Yamagishi, Junichi Tsao, Yu Wang, Hsin-Min |
| description | Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between converted speech and natural speech for voice conversion tasks. Unlike most neural evaluation metrics that use hand-crafted features, SVSNet directly takes the raw waveform as input to more completely utilize speech information for prediction. SVSNet consists of encoder, co-attention, distance calculation, and prediction modules and is trained in an end-to-end manner. The experimental results on the Voice Conversion Challenge 2018 and 2020 (VCC2018 and VCC2020) datasets show that SVSNet outperforms well-known baseline systems in the assessment of speaker similarity at the utterance and system levels. |
| doi_str_mv | 10.48550/arxiv.2107.09392 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2107_09392</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2553631931</sourcerecordid><originalsourceid>FETCH-LOGICAL-a521-57faeea69e638941c1ebf1141d1402ade0b0d823b4711bfa620f1a7fef38f0943</originalsourceid><addsrcrecordid>eNotz0tLAzEUBeAgCJbaH-DKgOuMuXnMw40MpVah6mJKt0OmuYGp8zKZiv339uHqbA6H8xFyBzxSqdb80fjf-icSwJOIZzITV2QipASWKiFuyCyEHedcxInQWk7Ic7EpPnB8onlHF51lY8-ws7QY0Hyhp5u-3iIt6rZujK_HA81DwBBa7Eb63ltsbsm1M03A2X9OyfplsZ6_stXn8m2er5jRAphOnEE0cYaxTDMFW8DKASiwoLgwFnnFbSpkpRKAyplYcAcmcehk6nim5JTcX2bPunLwdWv8oTwpy7Py2Hi4NAbff-8xjOWu3_vu-Kk8SWMJmQT5B5faU2M</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2553631931</pqid></control><display><type>article</type><title>SVSNet: An End-to-end Speaker Voice Similarity Assessment Model</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Cheng-Hung, Hu ; Yu-Huai Peng ; Yamagishi, Junichi ; Tsao, Yu ; Wang, Hsin-Min</creator><creatorcontrib>Cheng-Hung, Hu ; Yu-Huai Peng ; Yamagishi, Junichi ; Tsao, Yu ; Wang, Hsin-Min</creatorcontrib><description>Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between converted speech and natural speech for voice conversion tasks. Unlike most neural evaluation metrics that use hand-crafted features, SVSNet directly takes the raw waveform as input to more completely utilize speech information for prediction. SVSNet consists of encoder, co-attention, distance calculation, and prediction modules and is trained in an end-to-end manner. The experimental results on the Voice Conversion Challenge 2018 and 2020 (VCC2018 and VCC2020) datasets show that SVSNet outperforms well-known baseline systems in the assessment of speaker similarity at the utterance and system levels.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2107.09392</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Coders ; Computer Science - Learning ; Computer Science - Sound ; Evaluation ; Neural networks ; Similarity ; Speech recognition ; Waveforms</subject><ispartof>arXiv.org, 2022-02</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27904</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/LSP.2022.3152672$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2107.09392$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Cheng-Hung, Hu</creatorcontrib><creatorcontrib>Yu-Huai Peng</creatorcontrib><creatorcontrib>Yamagishi, Junichi</creatorcontrib><creatorcontrib>Tsao, Yu</creatorcontrib><creatorcontrib>Wang, Hsin-Min</creatorcontrib><title>SVSNet: An End-to-end Speaker Voice Similarity Assessment Model</title><title>arXiv.org</title><description>Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between converted speech and natural speech for voice conversion tasks. Unlike most neural evaluation metrics that use hand-crafted features, SVSNet directly takes the raw waveform as input to more completely utilize speech information for prediction. SVSNet consists of encoder, co-attention, distance calculation, and prediction modules and is trained in an end-to-end manner. The experimental results on the Voice Conversion Challenge 2018 and 2020 (VCC2018 and VCC2020) datasets show that SVSNet outperforms well-known baseline systems in the assessment of speaker similarity at the utterance and system levels.</description><subject>Coders</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Sound</subject><subject>Evaluation</subject><subject>Neural networks</subject><subject>Similarity</subject><subject>Speech recognition</subject><subject>Waveforms</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotz0tLAzEUBeAgCJbaH-DKgOuMuXnMw40MpVah6mJKt0OmuYGp8zKZiv339uHqbA6H8xFyBzxSqdb80fjf-icSwJOIZzITV2QipASWKiFuyCyEHedcxInQWk7Ic7EpPnB8onlHF51lY8-ws7QY0Hyhp5u-3iIt6rZujK_HA81DwBBa7Eb63ltsbsm1M03A2X9OyfplsZ6_stXn8m2er5jRAphOnEE0cYaxTDMFW8DKASiwoLgwFnnFbSpkpRKAyplYcAcmcehk6nim5JTcX2bPunLwdWv8oTwpy7Py2Hi4NAbff-8xjOWu3_vu-Kk8SWMJmQT5B5faU2M</recordid><startdate>20220217</startdate><enddate>20220217</enddate><creator>Cheng-Hung, Hu</creator><creator>Yu-Huai Peng</creator><creator>Yamagishi, Junichi</creator><creator>Tsao, Yu</creator><creator>Wang, Hsin-Min</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220217</creationdate><title>SVSNet: An End-to-end Speaker Voice Similarity Assessment Model</title><author>Cheng-Hung, Hu ; Yu-Huai Peng ; Yamagishi, Junichi ; Tsao, Yu ; Wang, Hsin-Min</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a521-57faeea69e638941c1ebf1141d1402ade0b0d823b4711bfa620f1a7fef38f0943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Coders</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Sound</topic><topic>Evaluation</topic><topic>Neural networks</topic><topic>Similarity</topic><topic>Speech recognition</topic><topic>Waveforms</topic><toplevel>online_resources</toplevel><creatorcontrib>Cheng-Hung, Hu</creatorcontrib><creatorcontrib>Yu-Huai Peng</creatorcontrib><creatorcontrib>Yamagishi, Junichi</creatorcontrib><creatorcontrib>Tsao, Yu</creatorcontrib><creatorcontrib>Wang, Hsin-Min</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cheng-Hung, Hu</au><au>Yu-Huai Peng</au><au>Yamagishi, Junichi</au><au>Tsao, Yu</au><au>Wang, Hsin-Min</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SVSNet: An End-to-end Speaker Voice Similarity Assessment Model</atitle><jtitle>arXiv.org</jtitle><date>2022-02-17</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Neural evaluation metrics derived for numerous speech generation tasks have recently attracted great attention. In this paper, we propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between converted speech and natural speech for voice conversion tasks. Unlike most neural evaluation metrics that use hand-crafted features, SVSNet directly takes the raw waveform as input to more completely utilize speech information for prediction. SVSNet consists of encoder, co-attention, distance calculation, and prediction modules and is trained in an end-to-end manner. The experimental results on the Voice Conversion Challenge 2018 and 2020 (VCC2018 and VCC2020) datasets show that SVSNet outperforms well-known baseline systems in the assessment of speaker similarity at the utterance and system levels.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2107.09392</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2022-02 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2107_09392 |
| source | arXiv.org; Free E- Journals |
| subjects | Coders Computer Science - Learning Computer Science - Sound Evaluation Neural networks Similarity Speech recognition Waveforms |
| title | SVSNet: An End-to-end Speaker Voice Similarity Assessment Model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T05%3A46%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SVSNet:%20An%20End-to-end%20Speaker%20Voice%20Similarity%20Assessment%20Model&rft.jtitle=arXiv.org&rft.au=Cheng-Hung,%20Hu&rft.date=2022-02-17&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2107.09392&rft_dat=%3Cproquest_arxiv%3E2553631931%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2553631931&rft_id=info:pmid/&rfr_iscdi=true |