{"id":"https://openalex.org/W4388821127","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317120","title":"Synthetic Data Augmentation for ASR with Domain Filtering","display_name":"Synthetic Data Augmentation for ASR with Domain Filtering","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821127","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317120"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317120","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317120","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":"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/A5083304186","display_name":"Tuan Vu Ho","orcid":"https://orcid.org/0000-0001-6819-0443"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tuan Vu Ho","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group,Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group,Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group,Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group,Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garcia","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084618194","display_name":"Takashi Sumiyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Sumiyoshi","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group,Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group,Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083304186"],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57698516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994000196456909,"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":0.9979000091552734,"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":0.8078690767288208},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6077454686164856},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5990760922431946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5521690249443054},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5327933430671692},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5093885064125061},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5043076276779175},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4989738464355469},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47300344705581665},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08874431252479553},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0743621289730072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078690767288208},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6077454686164856},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5990760922431946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5521690249443054},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5327933430671692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5093885064125061},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5043076276779175},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4989738464355469},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47300344705581665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08874431252479553},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0743621289730072},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/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/apsipaasc58517.2023.10317120","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317120","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":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989674786","https://openalex.org/W2184343439","https://openalex.org/W2250539671","https://openalex.org/W2407080277","https://openalex.org/W2747467128","https://openalex.org/W2883586237","https://openalex.org/W2885706078","https://openalex.org/W2894835365","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2940200615","https://openalex.org/W2948902769","https://openalex.org/W2962780374","https://openalex.org/W2963292011","https://openalex.org/W2964243274","https://openalex.org/W2970641574","https://openalex.org/W2998702515","https://openalex.org/W3008480565","https://openalex.org/W3015280134","https://openalex.org/W3015449694","https://openalex.org/W3015654635","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3096815019","https://openalex.org/W3097777922","https://openalex.org/W3162244132","https://openalex.org/W3198739096","https://openalex.org/W3198836239","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211278025","https://openalex.org/W4297841428","https://openalex.org/W6675409298","https://openalex.org/W6748150159","https://openalex.org/W6752906821","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W1997182898","https://openalex.org/W2327130486","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,109],"synthetic":[5,21],"speech":[6,15,22],"can":[7],"effectively":[8],"serve":[9],"as":[10],"training":[11],"data":[12,19,41],"for":[13,20],"automatic":[14],"recognition":[16],"models.":[17],"Text":[18],"is":[23,46],"mostly":[24],"obtained":[25],"from":[26,57,126],"in-domain":[27,39,91],"text":[28,31,40,56,72,82,92,101,116],"or":[29],"generated":[30],"using":[32,55,102],"augmentation.":[33],"However,":[34],"obtaining":[35],"large":[36,59],"amounts":[37],"of":[38,98,123],"with":[42,119],"diverse":[43],"lexical":[44],"contexts":[45],"difficult,":[47],"especially":[48],"in":[49],"low-resource":[50,138],"scenarios.":[51],"This":[52,74],"paper":[53],"proposes":[54],"a":[58,64,103,137],"generic-domain":[60],"source":[61],"and":[62,93,134],"applying":[63],"domain":[65],"filtering":[66,78],"method":[67,75,112],"to":[68,88,128],"choose":[69],"the":[70,89,96,99,114,120,131],"relevant":[71],"data.":[73],"involves":[76],"two":[77],"steps:":[79],"1)":[80],"selecting":[81],"based":[83],"on":[84,130,136],"its":[85],"semantic":[86],"similarity":[87],"available":[90],"2)":[94],"diversifying":[95],"vocabulary":[97],"selected":[100],"greedy-search":[104],"algorithm.":[105],"Experimental":[106],"results":[107],"show":[108],"our":[110],"proposed":[111],"outperforms":[113],"conventional":[115],"augmentation":[117],"approach,":[118],"relative":[121],"reduction":[122],"word-error-rate":[124],"ranging":[125],"6%":[127],"25%":[129],"LibriSpeech":[132],"dataset":[133],"15%":[135],"Vietnamese":[139],"dataset.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}