{"id":"https://openalex.org/W4402187093","doi":"https://doi.org/10.1109/taslp.2024.3451982","title":"Refining Synthesized Speech Using Speaker Information and Phone Masking for Data Augmentation of Speech Recognition","display_name":"Refining Synthesized Speech Using Speaker Information and Phone Masking for Data Augmentation of Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402187093","doi":"https://doi.org/10.1109/taslp.2024.3451982"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3451982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3451982","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/289487/1/TASLP.2024.3451982.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103835523","display_name":"Sei Ueno","orcid":"https://orcid.org/0000-0002-2255-3154"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sei Ueno","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya-shi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2255-3154","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya-shi, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035473671","display_name":"Akinobu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinobu Lee","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya-shi, Japan"],"raw_orcid":"https://orcid.org/0009-0005-5323-9191","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya-shi, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2686-2296","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8335,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77328734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"3924","last_page":"3933"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.813198983669281},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.732994794845581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7237043380737305},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6975787281990051},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5540062785148621},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5257471799850464},{"id":"https://openalex.org/keywords/refining","display_name":"Refining (metallurgy)","score":0.5115286111831665},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.48464709520339966},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3297809362411499},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3130154311656952},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07735949754714966}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.813198983669281},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.732994794845581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7237043380737305},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6975787281990051},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5540062785148621},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5257471799850464},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.5115286111831665},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.48464709520339966},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3297809362411499},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3130154311656952},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07735949754714966},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C147789679","wikidata":"https://www.wikidata.org/wiki/Q11372","display_name":"Physical chemistry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3451982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3451982","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:repository.kulib.kyoto-u.ac.jp:2433/289487","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/289487","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/289487/1/TASLP.2024.3451982.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:repository.kulib.kyoto-u.ac.jp:2433/289487","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/289487","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/289487/1/TASLP.2024.3451982.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2363020693","display_name":"A Study on Multi-modal Automatic Simultaneous Interpretation System and Evaluation Method","funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7760479039","display_name":"\u97f3\u58f0\u8a8d\u8b58\u306e\u30c7\u30fc\u30bf\u62e1\u5f35\u306e\u305f\u3081\u306e\u97f3\u58f0\u5408\u6210\u3068\u306e\u5bc6\u7d71\u5408","funder_award_id":"23K16944","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402187093.pdf","grobid_xml":"https://content.openalex.org/works/W4402187093.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2408688265","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2746654391","https://openalex.org/W2749514303","https://openalex.org/W2890964092","https://openalex.org/W2892009249","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2940200615","https://openalex.org/W2962699523","https://openalex.org/W2962759037","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2998781440","https://openalex.org/W3008191852","https://openalex.org/W3008480565","https://openalex.org/W3015280134","https://openalex.org/W3015449694","https://openalex.org/W3016185664","https://openalex.org/W3024464021","https://openalex.org/W3035574324","https://openalex.org/W3095189764","https://openalex.org/W3095687973","https://openalex.org/W3097828251","https://openalex.org/W3097890746","https://openalex.org/W3107298252","https://openalex.org/W3161296985","https://openalex.org/W3162244132","https://openalex.org/W3162512456","https://openalex.org/W3196869722","https://openalex.org/W3197294703","https://openalex.org/W3198836239","https://openalex.org/W3208049241","https://openalex.org/W4224930731","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6675365184","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6763832098","https://openalex.org/W6765987481","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6782760101","https://openalex.org/W6783182287"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"While":[0],"end-to-end":[1],"automatic":[2],"speech":[3,16,26,44,61,104,117],"recognition":[4],"(ASR)":[5],"has":[6,28],"shown":[7],"impressive":[8],"performance,":[9],"it":[10,67],"requires":[11,68],"a":[12,53,69,132,140,200,210],"huge":[13,70],"amount":[14,71],"of":[15,22,41,72,99,115,172],"and":[17,39,74,118,125,177],"transcription":[18],"data.":[19],"The":[20,37,191],"conversion":[21,76],"domain-matched":[23],"text":[24],"to":[25,34,59,77,121,160],"(TTS)":[27],"been":[29],"investigated":[30],"as":[31,81,131,145],"one":[32],"approach":[33],"data":[35],"augmentation.":[36],"quality":[38,124],"diversity":[40],"the":[42,82,96,111,116,123,161,170,187,206],"synthesized":[43],"are":[45],"critical":[46],"in":[47,63],"this":[48,92],"approach.":[49],"To":[50],"ensure":[51],"quality,":[52],"neural":[54],"vocoder":[55],"is":[56,129,158],"widely":[57],"used":[58,88],"generate":[60],"waveforms":[62],"conventional":[64,103,207],"studies,":[65],"but":[66],"computation":[73,203],"another":[75],"spectral-domain":[78],"features":[79,163],"such":[80,144],"log-Mel":[83],"filterbank":[84],"(lmfb)":[85],"output":[86],"typically":[87],"for":[89,164],"ASR.":[90],"In":[91],"study,":[93],"we":[94,106],"explore":[95],"direct":[97],"refinement":[98],"these":[100],"features.":[101],"Unlike":[102],"enhancement,":[105],"can":[107,136,151],"use":[108],"information":[109],"on":[110],"ground-truth":[112],"phone":[113,173],"sequences":[114],"designated":[119],"speaker":[120,175,181,189],"improve":[122],"diversity.":[126],"This":[127],"process":[128],"realized":[130],"Mel-to-Mel":[133],"network,":[134],"which":[135],"be":[137,152],"placed":[138],"after":[139],"text-to-Mel":[141],"synthesis":[142],"system":[143],"FastSpeech":[146],"2.":[147],"These":[148],"two":[149],"networks":[150],"trained":[153],"jointly.":[154],"Moreover,":[155],"semantic":[156,178],"masking":[157],"applied":[159],"lmfb":[162],"robust":[165],"training.":[166],"Experimental":[167],"evaluations":[168],"demonstrate":[169],"effect":[171],"information,":[174,176,182],"masking.":[179],"For":[180],"x-vector":[183],"performs":[184],"better":[185,196],"than":[186,205],"simple":[188],"embedding.":[190],"proposed":[192],"method":[193,208],"achieves":[194],"even":[195],"ASR":[197],"performance":[198],"with":[199],"much":[201],"shorter":[202],"time":[204],"using":[209],"vocoder.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}