{"id":"https://openalex.org/W3140429000","doi":"https://doi.org/10.21437/interspeech.2021-475","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","display_name":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3140429000","doi":"https://doi.org/10.21437/interspeech.2021-475","mag":"3140429000"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-475","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.00355","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":false,"raw_author_name":"Adam Polyak","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"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":"Yossi Adi","raw_affiliation_strings":["[Facebook AI Research, Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Facebook AI Research, Paris]","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020182193","display_name":"Jade Copet","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":"Jade Copet","raw_affiliation_strings":["[Facebook AI Research, Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Facebook AI Research, Paris]","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924622","display_name":"Eugene Kharitonov","orcid":"https://orcid.org/0009-0000-8653-721X"},"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":"Eugene Kharitonov","raw_affiliation_strings":["[Facebook AI Research, Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Facebook AI Research, Paris]","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050838145","display_name":"Kushal Lakhotia","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":"Kushal Lakhotia","raw_affiliation_strings":["[Facebook AI Research, Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Facebook AI Research, Paris]","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"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":"Wei-Ning Hsu","raw_affiliation_strings":["[Facebook AI Research, Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Facebook AI Research, Paris]","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","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":"Abdelrahman Mohamed","raw_affiliation_strings":["[Facebook AI Research, Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Facebook AI Research, Paris]","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"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":"Emmanuel Dupoux","raw_affiliation_strings":["Facebook AI Research [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research [Paris]","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":207,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3615","last_page":"3619"},"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":0.9998000264167786,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7967555522918701},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.7011844515800476},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7005848288536072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6963065266609192},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5624191761016846},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.494853675365448},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4473598599433899},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4426887333393097},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4294436275959015},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3956412076950073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38777047395706177},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3137032389640808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967555522918701},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.7011844515800476},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7005848288536072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6963065266609192},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5624191761016846},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.494853675365448},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4473598599433899},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4426887333393097},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4294436275959015},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3956412076950073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38777047395706177},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3137032389640808},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-475","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.00355","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00355","pdf_url":"https://arxiv.org/pdf/2104.00355","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.00355","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00355","pdf_url":"https://arxiv.org/pdf/2104.00355","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1498609987","https://openalex.org/W1885680957","https://openalex.org/W1959608418","https://openalex.org/W2097645910","https://openalex.org/W2107740512","https://openalex.org/W2114925438","https://openalex.org/W2115098197","https://openalex.org/W2120847449","https://openalex.org/W2130086727","https://openalex.org/W2292235217","https://openalex.org/W2527729766","https://openalex.org/W2750248772","https://openalex.org/W2775336875","https://openalex.org/W2808631503","https://openalex.org/W2842511635","https://openalex.org/W2890983311","https://openalex.org/W2924551963","https://openalex.org/W2935711438","https://openalex.org/W2940544976","https://openalex.org/W2944079609","https://openalex.org/W2949382160","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963618559","https://openalex.org/W2963799213","https://openalex.org/W2964167449","https://openalex.org/W2972867623","https://openalex.org/W2973049979","https://openalex.org/W2995181338","https://openalex.org/W3016098186","https://openalex.org/W3021164770","https://openalex.org/W3025878903","https://openalex.org/W3093427098","https://openalex.org/W3095361818","https://openalex.org/W3095948607","https://openalex.org/W3096216486","https://openalex.org/W3096323553","https://openalex.org/W3096656254","https://openalex.org/W3098403858","https://openalex.org/W3099782249","https://openalex.org/W3148101939","https://openalex.org/W3160799772","https://openalex.org/W3163296124","https://openalex.org/W3210177631"],"related_works":["https://openalex.org/W4319347033","https://openalex.org/W1890431648","https://openalex.org/W2020464095","https://openalex.org/W2106874932","https://openalex.org/W1911859126","https://openalex.org/W4386752790","https://openalex.org/W2365485488","https://openalex.org/W2040374013","https://openalex.org/W2151333624","https://openalex.org/W1548894166"],"abstract_inverted_index":{"We":[0,34],"propose":[1],"using":[2,73],"self-supervised":[3,38],"discrete":[4],"representations":[5,18,81],"for":[6,19,85],"the":[7,45,58,90,109,117],"task":[8],"of\\nspeech":[9],"resynthesis.":[10],"To":[11],"generate":[12],"disentangled":[13],"representation,":[14],"we":[15,56,93],"separately\\nextract":[16],"low-bitrate":[17],"speech":[20,30,106],"content,":[21],"prosodic":[22],"information,\\nand":[23],"speaker":[24,61],"identity.":[25],"This":[26],"allows":[27],"to":[28,96],"synthesize":[29],"in":[31],"a":[32,97],"controllable\\nmanner.":[33],"analyze":[35],"various":[36],"state-of-the-art,":[37],"representation\\nlearning":[39],"methods":[40],"and":[41,53,66,70],"shed":[42],"light":[43],"on":[44],"advantages":[46],"of":[47,99],"each":[48],"method":[49],"while\\nconsidering":[50],"reconstruction":[51],"quality":[52,72,107],"disentanglement":[54],"properties.\\nSpecifically,":[55],"evaluate":[57],"F0":[59],"reconstruction,":[60],"identification\\nperformance":[62],"(for":[63],"both":[64],"resynthesis":[65],"voice":[67],"conversion),":[68],"recordings'\\nintelligibility,":[69],"overall":[71],"subjective":[74],"human":[75],"evaluation.":[76],"Lastly,\\nwe":[77],"demonstrate":[78],"how":[79],"these":[80],"can":[82,94,113],"be":[83,114],"used":[84],"an":[86],"ultra-lightweight\\nspeech":[87],"codec.":[88],"Using":[89],"obtained":[91],"representations,":[92],"get":[95],"rate":[98],"365\\nbits":[100],"per":[101],"second":[102],"while":[103],"providing":[104],"better":[105],"than":[108],"baseline\\nmethods.":[110],"Audio":[111],"samples":[112],"found":[115],"under":[116],"following":[118],"link:\\nspeechbot.github.io/resynthesis.\\n":[119]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":64},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
