{"id":"https://openalex.org/W4388820459","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317116","title":"ASR Model Adaptation for Rare Words Using Synthetic Data Generated by Multiple Text-To-Speech Systems","display_name":"ASR Model Adaptation for Rare Words Using Synthetic Data Generated by Multiple Text-To-Speech Systems","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820459","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317116"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317116","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5113050150","display_name":"Kwok Chin Yuen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kwok Chin Yuen","raw_affiliation_strings":["Nangyang Technological University,Singapore","Nangyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nangyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nangyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037624853","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0003-3024-1350"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li Haoyang","raw_affiliation_strings":["Nangyang Technological University,Singapore","Nangyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nangyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nangyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chng Eng Siong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chng Eng Siong","raw_affiliation_strings":["Nangyang Technological University,Singapore","Nangyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nangyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nangyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1771","last_page":"1778"},"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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":0.7819413542747498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7295888066291809},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.58799809217453},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5731082558631897},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.552443265914917},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4760054051876068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46295979619026184},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45213738083839417},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4361329972743988},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3807220757007599},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09505784511566162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819413542747498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7295888066291809},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.58799809217453},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5731082558631897},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.552443265914917},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4760054051876068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46295979619026184},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45213738083839417},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4361329972743988},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3807220757007599},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09505784511566162},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317116","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1915251500","https://openalex.org/W2087006792","https://openalex.org/W2187428966","https://openalex.org/W2327501763","https://openalex.org/W2739883972","https://openalex.org/W2767052532","https://openalex.org/W2787663903","https://openalex.org/W2792643794","https://openalex.org/W2808706139","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2889012072","https://openalex.org/W2889326414","https://openalex.org/W2890964092","https://openalex.org/W2898599211","https://openalex.org/W2903739847","https://openalex.org/W2908510526","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2940200615","https://openalex.org/W2948210185","https://openalex.org/W2962780374","https://openalex.org/W2962788625","https://openalex.org/W2962826786","https://openalex.org/W2963362078","https://openalex.org/W2963882470","https://openalex.org/W2973072704","https://openalex.org/W3015440759","https://openalex.org/W3015449694","https://openalex.org/W3015654635","https://openalex.org/W3015826515","https://openalex.org/W3030485447","https://openalex.org/W3092028330","https://openalex.org/W3096815019","https://openalex.org/W3097777922","https://openalex.org/W3145157056","https://openalex.org/W3162244132","https://openalex.org/W3168997536","https://openalex.org/W3206375275","https://openalex.org/W4210327373","https://openalex.org/W4307079438","https://openalex.org/W4319586610","https://openalex.org/W4319862272","https://openalex.org/W4320930577","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6640059789","https://openalex.org/W6746023985","https://openalex.org/W6749029207","https://openalex.org/W6749555683","https://openalex.org/W6752888775","https://openalex.org/W6757817989","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6846500109","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W4388103534","https://openalex.org/W4312531262","https://openalex.org/W4318142952","https://openalex.org/W2072070946","https://openalex.org/W2944691285","https://openalex.org/W2146197305","https://openalex.org/W2134950286"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"for":[4],"rare":[5,164],"words":[6],"is":[7],"difficult":[8],"as":[9,235],"there":[10],"are":[11,29,121],"little":[12],"relevant":[13],"text-audio":[14,25],"data":[15,28,74,195,212,216],"pairs":[16],"to":[17,31,35,50,55,87,133,143,162,192,205,210,228],"train":[18],"an":[19,67,84],"ASR":[20,68,150,189,207],"model.":[21],"To":[22],"obtain":[23],"more":[24,72,145,155],"pairs,":[26],"text-only":[27],"fed":[30],"Text-To-Speech":[32],"(TTS)":[33],"systems":[34,103,113,137],"generate":[36],"synthetic":[37],"audio.":[38],"Previous":[39],"works":[40],"use":[41],"a":[42,140,163,187],"single":[43,141],"TTS":[44,102,112,136],"system":[45],"conditioned":[46,122],"on":[47,70,123,139],"multiple":[48,135],"speakers":[49],"produce":[51],"different":[52,101,111,115],"speaker":[53,60,94,116,142,147],"voices":[54],"improve":[56,79,88],"the":[57,71,80,89,93,107,124,206,214,223],"output":[58],"data\u2019s":[59],"diversity,":[61,90],"and":[62,78,104,178,218],"they":[63,120],"show":[64,185],"that":[65,106,186],"training":[66,236],"model":[69,190],"diverse":[73,146],"can":[75,152],"avoid":[76],"overfitting":[77],"model\u2019s":[81,224],"robustness.":[82],"As":[83],"alternative":[85],"way":[86],"we":[91,158],"study":[92],"embedding":[95],"distribution":[96],"of":[97,213],"audios":[98,108],"synthesized":[99,109],"by":[100,110,128],"found":[105],"have":[114],"distributions":[117],"even":[118],"when":[119],"same":[125,215],"speaker.":[126],"Inspired":[127],"this,":[129],"this":[130],"paper":[131],"proposes":[132],"condition":[134],"repeatedly":[138],"synthesize":[144],"data,":[148],"so":[149],"models":[151,208],"be":[153],"trained":[154],"robustly.":[156],"When":[157],"apply":[159],"our":[160,193,219],"method":[161],"word":[165,200],"dataset":[166],"partitioned":[167],"from":[168,226],"National":[169],"Speech":[170],"Corpus":[171],"SG,":[172],"which":[173],"contains":[174],"mostly":[175],"road":[176],"names":[177],"addresses":[179],"in":[180],"its":[181],"text":[182],"transcripts,":[183],"experiments":[184],"pretrained":[188],"adapted":[191,209],"multi-TTS-same-SPK":[194],"gives":[196],"relatively":[197],"9.8%":[198],"lower":[199],"error":[201],"rate":[202],"(WER)":[203],"compared":[204],"same-TTS-multi-SPK":[211],"size,":[217],"overall":[220],"adaptation":[221],"improves":[222],"WER":[225],"57.6%":[227],"16.5%":[229],"without":[230],"using":[231],"any":[232],"real":[233],"audio":[234],"data.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}