Comprehensive evaluation of statistical speech waveform synthesis
Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of SSWS is conducted across a number of domains to better...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2018-11 |
|---|---|
| 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 | Merritt, Thomas Putrycz, Bartosz Nadolski, Adam Ye, Tianjun Korzekwa, Daniel Dolecki, Wiktor Drugman, Thomas Klimkov, Viacheslav Moinet, Alexis Breen, Andrew Kuklinski, Rafal Strom, Nikko Barra-Chicote, Roberto |
| description | Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of SSWS is conducted across a number of domains to better understand the consistency in quality. The results of this evaluation are validated by repeating the procedure on a separate group of testers. Finally, an analysis of the nature of speech errors of SSWS compared to hybrid unit selection synthesis is conducted to identify the strengths and weaknesses of SSWS. Having a deeper insight into SSWS allows us to better define the focus of future work to improve this new technology. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2134094943</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2134094943</sourcerecordid><originalsourceid>FETCH-proquest_journals_21340949433</originalsourceid><addsrcrecordid>eNqNitEKwiAUQCUIGrV_EHoeOHXVHmMUfUDvQ8Ydczg1rxr9fXvoA3o6B87ZkIILUVcXyfmOlIgzY4yfzrxpREGunVt8gAks6gwUsjJJRe0sdSPFuCpGPShD0QMME32rDKMLC8WPjROgxgPZjsoglD_uyfF-e3aPygf3SoCxn10Kdk09r4VkrWylEP9dXxKxOqc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2134094943</pqid></control><display><type>article</type><title>Comprehensive evaluation of statistical speech waveform synthesis</title><source>Free E- Journals</source><creator>Merritt, Thomas ; Putrycz, Bartosz ; Nadolski, Adam ; Ye, Tianjun ; Korzekwa, Daniel ; Dolecki, Wiktor ; Drugman, Thomas ; Klimkov, Viacheslav ; Moinet, Alexis ; Breen, Andrew ; Kuklinski, Rafal ; Strom, Nikko ; Barra-Chicote, Roberto</creator><creatorcontrib>Merritt, Thomas ; Putrycz, Bartosz ; Nadolski, Adam ; Ye, Tianjun ; Korzekwa, Daniel ; Dolecki, Wiktor ; Drugman, Thomas ; Klimkov, Viacheslav ; Moinet, Alexis ; Breen, Andrew ; Kuklinski, Rafal ; Strom, Nikko ; Barra-Chicote, Roberto</creatorcontrib><description>Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of SSWS is conducted across a number of domains to better understand the consistency in quality. The results of this evaluation are validated by repeating the procedure on a separate group of testers. Finally, an analysis of the nature of speech errors of SSWS compared to hybrid unit selection synthesis is conducted to identify the strengths and weaknesses of SSWS. Having a deeper insight into SSWS allows us to better define the focus of future work to improve this new technology.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Domains ; New technology ; Speech recognition ; Synthesis</subject><ispartof>arXiv.org, 2018-11</ispartof><rights>2018. 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><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>776,780</link.rule.ids></links><search><creatorcontrib>Merritt, Thomas</creatorcontrib><creatorcontrib>Putrycz, Bartosz</creatorcontrib><creatorcontrib>Nadolski, Adam</creatorcontrib><creatorcontrib>Ye, Tianjun</creatorcontrib><creatorcontrib>Korzekwa, Daniel</creatorcontrib><creatorcontrib>Dolecki, Wiktor</creatorcontrib><creatorcontrib>Drugman, Thomas</creatorcontrib><creatorcontrib>Klimkov, Viacheslav</creatorcontrib><creatorcontrib>Moinet, Alexis</creatorcontrib><creatorcontrib>Breen, Andrew</creatorcontrib><creatorcontrib>Kuklinski, Rafal</creatorcontrib><creatorcontrib>Strom, Nikko</creatorcontrib><creatorcontrib>Barra-Chicote, Roberto</creatorcontrib><title>Comprehensive evaluation of statistical speech waveform synthesis</title><title>arXiv.org</title><description>Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of SSWS is conducted across a number of domains to better understand the consistency in quality. The results of this evaluation are validated by repeating the procedure on a separate group of testers. Finally, an analysis of the nature of speech errors of SSWS compared to hybrid unit selection synthesis is conducted to identify the strengths and weaknesses of SSWS. Having a deeper insight into SSWS allows us to better define the focus of future work to improve this new technology.</description><subject>Domains</subject><subject>New technology</subject><subject>Speech recognition</subject><subject>Synthesis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNitEKwiAUQCUIGrV_EHoeOHXVHmMUfUDvQ8Ydczg1rxr9fXvoA3o6B87ZkIILUVcXyfmOlIgzY4yfzrxpREGunVt8gAks6gwUsjJJRe0sdSPFuCpGPShD0QMME32rDKMLC8WPjROgxgPZjsoglD_uyfF-e3aPygf3SoCxn10Kdk09r4VkrWylEP9dXxKxOqc</recordid><startdate>20181115</startdate><enddate>20181115</enddate><creator>Merritt, Thomas</creator><creator>Putrycz, Bartosz</creator><creator>Nadolski, Adam</creator><creator>Ye, Tianjun</creator><creator>Korzekwa, Daniel</creator><creator>Dolecki, Wiktor</creator><creator>Drugman, Thomas</creator><creator>Klimkov, Viacheslav</creator><creator>Moinet, Alexis</creator><creator>Breen, Andrew</creator><creator>Kuklinski, Rafal</creator><creator>Strom, Nikko</creator><creator>Barra-Chicote, Roberto</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></search><sort><creationdate>20181115</creationdate><title>Comprehensive evaluation of statistical speech waveform synthesis</title><author>Merritt, Thomas ; Putrycz, Bartosz ; Nadolski, Adam ; Ye, Tianjun ; Korzekwa, Daniel ; Dolecki, Wiktor ; Drugman, Thomas ; Klimkov, Viacheslav ; Moinet, Alexis ; Breen, Andrew ; Kuklinski, Rafal ; Strom, Nikko ; Barra-Chicote, Roberto</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_21340949433</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Domains</topic><topic>New technology</topic><topic>Speech recognition</topic><topic>Synthesis</topic><toplevel>online_resources</toplevel><creatorcontrib>Merritt, Thomas</creatorcontrib><creatorcontrib>Putrycz, Bartosz</creatorcontrib><creatorcontrib>Nadolski, Adam</creatorcontrib><creatorcontrib>Ye, Tianjun</creatorcontrib><creatorcontrib>Korzekwa, Daniel</creatorcontrib><creatorcontrib>Dolecki, Wiktor</creatorcontrib><creatorcontrib>Drugman, Thomas</creatorcontrib><creatorcontrib>Klimkov, Viacheslav</creatorcontrib><creatorcontrib>Moinet, Alexis</creatorcontrib><creatorcontrib>Breen, Andrew</creatorcontrib><creatorcontrib>Kuklinski, Rafal</creatorcontrib><creatorcontrib>Strom, Nikko</creatorcontrib><creatorcontrib>Barra-Chicote, Roberto</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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Merritt, Thomas</au><au>Putrycz, Bartosz</au><au>Nadolski, Adam</au><au>Ye, Tianjun</au><au>Korzekwa, Daniel</au><au>Dolecki, Wiktor</au><au>Drugman, Thomas</au><au>Klimkov, Viacheslav</au><au>Moinet, Alexis</au><au>Breen, Andrew</au><au>Kuklinski, Rafal</au><au>Strom, Nikko</au><au>Barra-Chicote, Roberto</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Comprehensive evaluation of statistical speech waveform synthesis</atitle><jtitle>arXiv.org</jtitle><date>2018-11-15</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of SSWS is conducted across a number of domains to better understand the consistency in quality. The results of this evaluation are validated by repeating the procedure on a separate group of testers. Finally, an analysis of the nature of speech errors of SSWS compared to hybrid unit selection synthesis is conducted to identify the strengths and weaknesses of SSWS. Having a deeper insight into SSWS allows us to better define the focus of future work to improve this new technology.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2018-11 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2134094943 |
| source | Free E- Journals |
| subjects | Domains New technology Speech recognition Synthesis |
| title | Comprehensive evaluation of statistical speech waveform synthesis |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T13%3A12%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Comprehensive%20evaluation%20of%20statistical%20speech%20waveform%20synthesis&rft.jtitle=arXiv.org&rft.au=Merritt,%20Thomas&rft.date=2018-11-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2134094943%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2134094943&rft_id=info:pmid/&rfr_iscdi=true |