{"id":"https://openalex.org/W2972970915","doi":"https://doi.org/10.21437/interspeech.2019-1789","title":"Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation","display_name":"Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972970915","doi":"https://doi.org/10.21437/interspeech.2019-1789","mag":"2972970915"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055592425","display_name":"Fadi Biadsy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fadi Biadsy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002011583","display_name":"D. Kanvesky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitri Kanvesky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102792436","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-8000-4911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4115","last_page":"4119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8651000261306763,"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":0.8651000261306763,"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":0.8363000154495239,"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":0.6375371217727661},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5348206162452698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4988269805908203},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4721272885799408},{"id":"https://openalex.org/keywords/hearing-impaired","display_name":"Hearing impaired","score":0.4604950249195099},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4544532597064972},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.44854140281677246},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42183718085289},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.2291552722454071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1393105685710907},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.05162331461906433},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.046816229820251465}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6375371217727661},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5348206162452698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4988269805908203},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4721272885799408},{"id":"https://openalex.org/C3020736805","wikidata":"https://www.wikidata.org/wiki/Q16035842","display_name":"Hearing impaired","level":2,"score":0.4604950249195099},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4544532597064972},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.44854140281677246},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42183718085289},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.2291552722454071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1393105685710907},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.05162331461906433},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.046816229820251465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W46785905","https://openalex.org/W87473629","https://openalex.org/W190138384","https://openalex.org/W854541894","https://openalex.org/W1485009520","https://openalex.org/W1836465849","https://openalex.org/W1963778986","https://openalex.org/W2005768155","https://openalex.org/W2007908237","https://openalex.org/W2013996527","https://openalex.org/W2017742648","https://openalex.org/W2114543868","https://openalex.org/W2120847449","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2142300631","https://openalex.org/W2221409856","https://openalex.org/W2327501763","https://openalex.org/W2465174275","https://openalex.org/W2530876040","https://openalex.org/W2605131327","https://openalex.org/W2808706139","https://openalex.org/W2962824709","https://openalex.org/W2963011080","https://openalex.org/W2963609956","https://openalex.org/W2963902628","https://openalex.org/W2964243274","https://openalex.org/W4289299319","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4299563208"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W3013209356","https://openalex.org/W2089240210","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2161396743","https://openalex.org/W1909292483"],"abstract_inverted_index":{"We":[0],"describe":[1],"Parrotron,":[2],"an":[3,10,27],"end-to-end-trained":[4],"speech-to-speech":[5],"conversion":[6],"model":[7,45,85,119,129],"that":[8,43,82,126],"maps":[9],"input":[11],"spectrogram":[12,29],"directly":[13],"to":[14,37,49,89,134],"another":[15],"spectrogram,":[16],"without":[17],"utilizing":[18],"any":[19,53],"intermediate":[20],"discrete":[21],"representation.The":[22],"network":[23],"is":[24],"composed":[25],"of":[26,56,65,117],"encoder,":[28],"and":[30,59,75,78,104,111],"phoneme":[31],"decoders,":[32],"followed":[33],"by":[34],"a":[35,39,66,72,95,108,136],"vocoder":[36],"synthesize":[38],"time-domain":[40],"waveform.We":[41],"demonstrate":[42],"this":[44,83,118],"can":[46,86,131],"be":[47,87,132],"trained":[48,133],"normalize":[50,90],"speech":[51,93,109,122,137],"from":[52,94],"speaker":[54,70],"regardless":[55],"accent,":[57],"prosody,":[58],"background":[60],"noise,":[61],"into":[62],"the":[63,115,127],"voice":[64],"single":[67],"canonical":[68],"target":[69],"with":[71],"fixed":[73],"accent":[74],"consistent":[76],"articulation":[77],"prosody.We":[79],"further":[80],"show":[81,125],"normalization":[84],"adapted":[88],"highly":[91],"atypical":[92],"deaf":[96],"speaker,":[97],"resulting":[98],"in":[99,102],"significant":[100],"improvements":[101],"intelligibility":[103],"naturalness,":[105],"measured":[106],"via":[107],"recognizer":[110],"listening":[112],"tests.Finally,":[113],"demonstrating":[114],"utility":[116],"on":[120],"other":[121],"tasks,":[123],"we":[124],"same":[128],"architecture":[130],"perform":[135],"separation":[138],"task.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}