{"id":"https://openalex.org/W2939354923","doi":"https://doi.org/10.21437/interspeech.2020-1416","title":"TTS Skins: Speaker Conversion via ASR","display_name":"TTS Skins: Speaker Conversion via ASR","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W2939354923","doi":"https://doi.org/10.21437/interspeech.2020-1416","mag":"2939354923"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1416","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.08983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038017098","display_name":"Adam Polyak","orcid":"https://orcid.org/0000-0003-2563-2111"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Adam Polyak","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070563684","display_name":"Yaniv Taigman","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yaniv Taigman","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038017098"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":0.5486,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72108839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"786","last_page":"790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7720531821250916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745853841304779},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7425480484962463},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6490678787231445},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.623399019241333},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.526569128036499},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.44911468029022217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3523125648498535},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11552852392196655},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0643511712551117}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7720531821250916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745853841304779},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7425480484962463},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6490678787231445},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.623399019241333},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.526569128036499},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.44911468029022217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3523125648498535},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11552852392196655},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0643511712551117},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1416","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.08983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08983","pdf_url":"https://arxiv.org/pdf/1904.08983","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2939354923","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1904.08983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.08983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.08983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.08983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08983","pdf_url":"https://arxiv.org/pdf/1904.08983","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2939354923.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1959608418","https://openalex.org/W2026369565","https://openalex.org/W2150769028","https://openalex.org/W2160473997","https://openalex.org/W2161476805","https://openalex.org/W2171019095","https://openalex.org/W2397499194","https://openalex.org/W2471520273","https://openalex.org/W2518172956","https://openalex.org/W2518312472","https://openalex.org/W2520160253","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2606176153","https://openalex.org/W2651834199","https://openalex.org/W2739748921","https://openalex.org/W2777302760","https://openalex.org/W2796495654","https://openalex.org/W2802935216","https://openalex.org/W2804998325","https://openalex.org/W2889329491","https://openalex.org/W2890402938","https://openalex.org/W2901739041","https://openalex.org/W2919752630","https://openalex.org/W2949382160","https://openalex.org/W2962739369","https://openalex.org/W2962896155","https://openalex.org/W2963233633","https://openalex.org/W2963432880","https://openalex.org/W2963534259","https://openalex.org/W2963712897","https://openalex.org/W2963799213","https://openalex.org/W2963821905","https://openalex.org/W2963912924","https://openalex.org/W2964227577","https://openalex.org/W2972359262","https://openalex.org/W2973142754","https://openalex.org/W2973215447"],"related_works":["https://openalex.org/W3096323553","https://openalex.org/W3090528452","https://openalex.org/W2963712897","https://openalex.org/W3174954176","https://openalex.org/W2959758584","https://openalex.org/W2955833882","https://openalex.org/W2900295214","https://openalex.org/W2934995906","https://openalex.org/W2944782944","https://openalex.org/W3162046328","https://openalex.org/W3114691655","https://openalex.org/W2031182901","https://openalex.org/W2117883790","https://openalex.org/W2381853352","https://openalex.org/W3134422648","https://openalex.org/W2786105640","https://openalex.org/W3003750857","https://openalex.org/W2744799066","https://openalex.org/W2362638775","https://openalex.org/W3167596786"],"abstract_inverted_index":{"We":[0,52],"present":[1],"a":[2,37,71],"fully":[3],"convolutional":[4],"wav-to-wav":[5],"network":[6,17,55],"for":[7,29],"converting":[8,67],"between":[9],"speakers'":[10],"voices,":[11,65],"without":[12],"relying":[13],"on":[14,20,56],"text.":[15],"Our":[16],"is":[18,27,41],"based":[19],"an":[21,49],"encoder-decoder":[22],"architecture,":[23],"where":[24],"the":[25,30,45,54,68],"encoder":[26],"pre-trained":[28],"task":[31],"of":[32,70],"Automatic":[33],"Speech":[34],"Recognition,":[35],"and":[36,59],"multi-speaker":[38],"waveform":[39],"decoder":[40],"trained":[42],"to":[43],"reconstruct":[44],"original":[46],"signal":[47],"in":[48,63],"autoregressive":[50],"manner.":[51],"train":[53],"narrated":[57],"audiobooks,":[58],"demonstrate":[60],"multi-voice":[61],"TTS":[62,72],"those":[64],"by":[66],"voice":[69],"robot.":[73]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}