{"id":"https://openalex.org/W3161018648","doi":"https://doi.org/10.1109/icassp39728.2021.9414644","title":"Extending Parrotron: An End-to-End, Speech Conversion and Speech Recognition Model for Atypical Speech","display_name":"Extending Parrotron: An End-to-End, Speech Conversion and Speech Recognition Model for Atypical Speech","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161018648","doi":"https://doi.org/10.1109/icassp39728.2021.9414644","mag":"3161018648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414644","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":"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/A5062360652","display_name":"Rohan Doshi","orcid":"https://orcid.org/0009-0005-4923-825X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Doshi","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018757219","display_name":"Youzheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youzheng Chen","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064222829","display_name":"Liyang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liyang Jiang","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101588866","display_name":"Xia Zhang","orcid":"https://orcid.org/0000-0002-4313-600X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xia Zhang","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055592425","display_name":"Fadi Biadsy","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fadi Biadsy","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111484288","display_name":"Fang Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Chu","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6988","last_page":"6992"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.814582884311676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746785879135132},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7691630125045776},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5261542201042175},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5168402791023254},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4880134165287018},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.43549424409866333},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42934364080429077},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3639168441295624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34605467319488525},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.061466336250305176}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.814582884311676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746785879135132},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7691630125045776},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5261542201042175},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5168402791023254},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4880134165287018},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.43549424409866333},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42934364080429077},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3639168441295624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34605467319488525},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.061466336250305176},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414644","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2005768155","https://openalex.org/W2007908237","https://openalex.org/W2069324367","https://openalex.org/W2073393345","https://openalex.org/W2109848220","https://openalex.org/W2120847449","https://openalex.org/W2142300631","https://openalex.org/W2747467128","https://openalex.org/W2798571323","https://openalex.org/W2883245269","https://openalex.org/W2888807255","https://openalex.org/W2936774411","https://openalex.org/W2936861580","https://openalex.org/W2962760690","https://openalex.org/W2963382687","https://openalex.org/W2963403868","https://openalex.org/W2964243274","https://openalex.org/W2964525587","https://openalex.org/W2972689158","https://openalex.org/W2972725946","https://openalex.org/W2972838300","https://openalex.org/W2972970915","https://openalex.org/W2973051376","https://openalex.org/W2997354053","https://openalex.org/W2999996462","https://openalex.org/W3008480565","https://openalex.org/W3012461590","https://openalex.org/W3015693260","https://openalex.org/W3015707856","https://openalex.org/W3015974384","https://openalex.org/W4385245566","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W596245619"],"abstract_inverted_index":{"We":[0,40,59,92],"present":[1],"an":[2,66,108],"extended":[3],"Parrotron":[4],"model:":[5],"a":[6,28,37,75,99,132],"single,":[7],"end-to-end":[8],"network":[9],"that":[10,61,95],"enables":[11],"voice":[12,26],"conversion":[13],"and":[14,52],"recognition":[15],"simultaneously.":[16],"Input":[17],"spectrograms":[18,23],"are":[19],"transformed":[20],"to":[21],"output":[22],"in":[24,36,79],"the":[25,42,89,114],"of":[27,44,68,128,134],"predetermined":[29],"target":[30,38],"speaker":[31,71],"while":[32],"also":[33,93],"generating":[34],"hypotheses":[35],"vocabulary.":[39],"study":[41],"performance":[43,87],"this":[45],"novel":[46],"architecture,":[47],"which":[48],"jointly":[49],"predicts":[50],"speech":[51,105,130,135],"text,":[53],"on":[54,88,103],"atypical":[55,69,104,129],"(e.g.":[56],"dysarthric)":[57],"speech.":[58,91],"show":[60,94,120],"with":[62],"as":[63,65],"little":[64],"hour":[67],"speech,":[70],"adaptation":[72],"can":[73,106],"yield":[74],"77%":[76],"relative":[77,111],"reduction":[78],"Word":[80],"Error":[81],"Rate":[82],"(WER),":[83],"measured":[84],"by":[85],"ASR":[86],"converted":[90],"data":[96],"augmentation":[97],"using":[98],"customized":[100],"synthesizer":[101],"built":[102],"provide":[107],"additional":[109],"10%":[110],"improvement":[112],"over":[113],"best":[115],"speaker-adapted":[116],"model.":[117],"Finally,":[118],"we":[119],"how":[121],"these":[122],"methods":[123],"generalize":[124],"across":[125],"8":[126],"types":[127],"for":[131],"range":[133],"impairment":[136],"severities.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
