{"id":"https://openalex.org/W3016008406","doi":"https://doi.org/10.1109/icassp40776.2020.9053104","title":"Using Personalized Speech Synthesis and Neural Language Generator for Rapid Speaker Adaptation","display_name":"Using Personalized Speech Synthesis and Neural Language Generator for Rapid Speaker Adaptation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016008406","doi":"https://doi.org/10.1109/icassp40776.2020.9053104","mag":"3016008406"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100764456","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-0575-0156"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055564488","display_name":"Wenning Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Wenning Wei","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068671901","display_name":"William A. Gale","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"William Gale","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100764456"],"corresponding_institution_ids":["https://openalex.org/I4210105678"],"apc_list":null,"apc_paid":null,"fwci":2.5186,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9125791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7399","last_page":"7403"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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/T12031","display_name":"Speech and dialogue systems","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7926953434944153},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7445618510246277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7281995415687561},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5844476819038391},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48413047194480896},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.47343873977661133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46928533911705017},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4648273289203644},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4224061965942383},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09413307905197144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07017642259597778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926953434944153},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7445618510246277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7281995415687561},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5844476819038391},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48413047194480896},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.47343873977661133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46928533911705017},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4648273289203644},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4224061965942383},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09413307905197144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07017642259597778},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W567546468","https://openalex.org/W1509793305","https://openalex.org/W1513862252","https://openalex.org/W1571447047","https://openalex.org/W1961429348","https://openalex.org/W1979651826","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2010362084","https://openalex.org/W2056738732","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2397860787","https://openalex.org/W2399832792","https://openalex.org/W2402268235","https://openalex.org/W2508162385","https://openalex.org/W2519091744","https://openalex.org/W2889182644","https://openalex.org/W2889374926","https://openalex.org/W2903853691","https://openalex.org/W2916997151","https://openalex.org/W2939173691","https://openalex.org/W2949382160","https://openalex.org/W2949555952","https://openalex.org/W2962784628","https://openalex.org/W2963609956","https://openalex.org/W2964182776","https://openalex.org/W2964243274","https://openalex.org/W3125118953","https://openalex.org/W6615969787","https://openalex.org/W6634371499","https://openalex.org/W6638575559","https://openalex.org/W6639822467","https://openalex.org/W6712756720","https://openalex.org/W6713098461","https://openalex.org/W6724991294","https://openalex.org/W6728274705","https://openalex.org/W6736996214","https://openalex.org/W6757322325"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"We":[0,97],"propose":[1],"to":[2,13,63,102,142],"use":[3,41],"the":[4,9,31,50,53,69,81,92,99,135,138,143,170,173],"personalized":[5,17,45,82],"speech":[6,18,78,110],"synthesis":[7],"and":[8,137],"neural":[10],"language":[11],"generator":[12],"synthesize":[14],"content":[15],"relevant":[16],"for":[19,134,182],"rapid":[20,37,93],"speaker":[21,95,104],"adaptation.":[22,65,96,175,184],"It":[23],"has":[24],"two":[25],"distinct":[26],"aspects:":[27],"First,":[28],"it":[29,48,62,159],"relieves":[30],"general":[32],"data":[33],"sparsity":[34],"issue":[35],"in":[36,57,80,87,91,107],"adaptation":[38,59,105,117,157],"via":[39],"making":[40],"of":[42,52,172],"additional":[43],"synthesized":[44,83],"speech;":[46],"Second,":[47],"circumvents":[49],"obstacle":[51],"explicit":[54],"labeling":[55,70],"error":[56,71,130],"unsupervised":[58,94,139,183],"by":[60],"converting":[61],"pseudo-supervised":[64],"In":[66],"this":[67],"setup,":[68],"is":[72,179],"implicitly":[73],"rendered":[74],"as":[75],"less":[76],"damaging":[77],"distortion":[79],"speech.":[84,153],"This":[85],"results":[86],"significant":[88],"performance":[89],"breakthrough":[90],"apply":[98],"proposed":[100,120,177],"methodology":[101],"a":[103,108],"task":[106],"state-of-art":[109],"transcription":[111],"system.":[112],"With":[113,154],"1":[114,150],"minute":[115],"(min)":[116],"data,":[118,158],"our":[119],"approach":[121,178],"yields":[122,160],"9.19":[123],"%":[124,127,162,165],"or":[125,163],"5.98":[126],"relative":[128,166],"word":[129],"rate":[131],"(WER)":[132],"reduction":[133],"supervised":[136],"adaptation,":[140],"comparing":[141],"negligible":[144],"gain":[145,171],"when":[146],"adapting":[147],"only":[148],"with":[149],"min":[151,156],"original":[152],"10":[155],"12.53":[161],"7.89":[164],"WER":[167],"reduction,":[168],"doubling":[169],"baseline":[174],"The":[176],"particularly":[180],"suitable":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}