{"id":"https://openalex.org/W3127113664","doi":"https://doi.org/10.1109/icassp39728.2021.9414853","title":"High Fidelity Speech Regeneration with Application to Speech Enhancement","display_name":"High Fidelity Speech Regeneration with Application to Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3127113664","doi":"https://doi.org/10.1109/icassp39728.2021.9414853","mag":"3127113664"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2102.00429","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/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]},{"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 AI Research","The School of Computer Science, Tel Aviv University","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"The School of Computer Science, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","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"]},{"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":"Lior Wolf","raw_affiliation_strings":["Facebook AI Research","The School of Computer Science, Tel Aviv University","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"The School of Computer Science, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","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","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087825391","display_name":"Ori Kabeli","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":"Ori Kabeli","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"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":["Facebook AI Research","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038017098"],"corresponding_institution_ids":["https://openalex.org/I16391192","https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01456767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7143","last_page":"7147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.7425216436386108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183677554130554},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.653389573097229},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6227232813835144},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5067253708839417},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4554360508918762},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4354703426361084},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4316522777080536},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.41965097188949585},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2896198630332947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2623109519481659},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18853381276130676},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09436294436454773}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7425216436386108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183677554130554},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.653389573097229},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6227232813835144},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5067253708839417},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4554360508918762},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4354703426361084},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4316522777080536},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.41965097188949585},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2896198630332947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2623109519481659},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18853381276130676},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09436294436454773},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.00429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00429","pdf_url":"https://arxiv.org/pdf/2102.00429","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:3127113664","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.00429.pdf","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.2102.00429","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.00429","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"},{"id":"doi:10.17023/dy3g-7123","is_oa":true,"landing_page_url":"https://doi.org/10.17023/dy3g-7123","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2102.00429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00429","pdf_url":"https://arxiv.org/pdf/2102.00429","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3127113664.pdf","grobid_xml":"https://content.openalex.org/works/W3127113664.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2086381917","https://openalex.org/W2110165814","https://openalex.org/W2115098197","https://openalex.org/W2133908567","https://openalex.org/W2147152002","https://openalex.org/W2193413348","https://openalex.org/W2520160253","https://openalex.org/W2527729766","https://openalex.org/W2545656684","https://openalex.org/W2593414223","https://openalex.org/W2757519008","https://openalex.org/W2802304149","https://openalex.org/W2808631503","https://openalex.org/W2939253202","https://openalex.org/W2943895317","https://openalex.org/W2944438111","https://openalex.org/W2962788625","https://openalex.org/W2963103134","https://openalex.org/W2963836885","https://openalex.org/W2972707556","https://openalex.org/W2973133192","https://openalex.org/W2973215447","https://openalex.org/W2974831423","https://openalex.org/W2975414524","https://openalex.org/W2994143516","https://openalex.org/W2996286887","https://openalex.org/W3015338123","https://openalex.org/W3015837673","https://openalex.org/W3046970875","https://openalex.org/W3096159803","https://openalex.org/W3096323553","https://openalex.org/W3097945073","https://openalex.org/W3141523618","https://openalex.org/W3209141406","https://openalex.org/W4232282348","https://openalex.org/W6680017764","https://openalex.org/W6682013673","https://openalex.org/W6687566353","https://openalex.org/W6727336983","https://openalex.org/W6729110096","https://openalex.org/W6748582592","https://openalex.org/W6751512325","https://openalex.org/W6762114000","https://openalex.org/W6770958331","https://openalex.org/W6781251213","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W3163296124","https://openalex.org/W3210917154","https://openalex.org/W1492258091","https://openalex.org/W925747522","https://openalex.org/W2240622083","https://openalex.org/W2738035098","https://openalex.org/W2148579858","https://openalex.org/W2771275309","https://openalex.org/W170089077","https://openalex.org/W2736031499","https://openalex.org/W1500640442","https://openalex.org/W2998072428","https://openalex.org/W1571887930","https://openalex.org/W2184152089","https://openalex.org/W3104309246","https://openalex.org/W2398264106","https://openalex.org/W3126260881","https://openalex.org/W73873779","https://openalex.org/W2577762507","https://openalex.org/W3163906773"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"has":[2],"seen":[3],"great":[4],"improvement":[5],"in":[6,12,43,73],"recent":[7,135],"years":[8],"mainly":[9],"through":[10],"contributions":[11],"denoising,":[13],"speaker":[14],"separation,":[15],"and":[16,58,77,87,124],"dereverberation":[17],"methods":[18],"that":[19,68,128],"mostly":[20],"deal":[21],"with":[22],"environmental":[23],"effects":[24],"on":[25],"vocal":[26],"audio.":[27],"To":[28],"enhance":[29],"speech":[30,48,67,72,82,107],"beyond":[31],"the":[32,35,47,53,106,111,114,129],"limitations":[33],"of":[34,85,95,113],"original":[36],"signal,":[37],"we":[38,45,102],"take":[39],"a":[40,62,74,80,92],"regeneration":[41],"approach,":[42],"which":[44,78],"recreate":[46],"from":[49],"its":[50],"essence,":[51],"including":[52],"semi-recognized":[54],"speech,":[55],"prosody":[56],"features,":[57,89],"identity.":[59],"We":[60],"propose":[61],"wav-to-wav":[63],"generative":[64],"model":[65],"for":[66],"can":[69],"generate":[70],"24khz":[71],"real-time":[75],"manner":[76],"utilizes":[79],"compact":[81],"representation,":[83],"composed":[84],"ASR":[86],"identity":[88,112,119],"to":[90,104],"achieve":[91],"higher":[93],"level":[94],"intelligibility.":[96],"Inspired":[97],"by":[98],"voice":[99],"conversion":[100],"methods,":[101],"train":[103],"augment":[105],"characteristics":[108],"while":[109],"preserving":[110],"source":[115],"using":[116],"an":[117],"auxiliary":[118],"network.":[120],"Perceptual":[121],"acoustic":[122],"metrics":[123],"subjective":[125],"tests":[126],"show":[127],"method":[130],"obtains":[131],"valuable":[132],"improvements":[133],"over":[134],"baselines.":[136]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}