{"id":"https://openalex.org/W4391021545","doi":"https://doi.org/10.1109/asru57964.2023.10389617","title":"Zero-Shot Domain-Sensitive Speech Recognition with Prompt-Conditioning Fine-Tuning","display_name":"Zero-Shot Domain-Sensitive Speech Recognition with Prompt-Conditioning Fine-Tuning","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021545","doi":"https://doi.org/10.1109/asru57964.2023.10389617"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5067740015","display_name":"Feng-Ting Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng-Ting Liao","raw_affiliation_strings":["MediaTek Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293964","display_name":"Yung-Chieh Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yung-Chieh Chan","raw_affiliation_strings":["MediaTek Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006096139","display_name":"Yi\u2010Chang Chen","orcid":"https://orcid.org/0000-0003-1380-3737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Chang Chen","raw_affiliation_strings":["MediaTek Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059902893","display_name":"Chan-Jan Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chan-Jan Hsu","raw_affiliation_strings":["MediaTek Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104231268","display_name":"Da-shan Shiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Da-Shan Shiu","raw_affiliation_strings":["MediaTek Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7948,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8839259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9947999715805054,"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":0.6689066290855408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5873993635177612},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5438211560249329},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.49341192841529846},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46408435702323914},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.4386114180088043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816347122192383},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11813896894454956},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10967448353767395},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06323951482772827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689066290855408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5873993635177612},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5438211560249329},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.49341192841529846},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46408435702323914},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.4386114180088043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816347122192383},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11813896894454956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10967448353767395},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06323951482772827},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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/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/asru57964.2023.10389617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2560647685","https://openalex.org/W2916984808","https://openalex.org/W3001279689","https://openalex.org/W3030437843","https://openalex.org/W3085355042","https://openalex.org/W3161860537","https://openalex.org/W3197608144","https://openalex.org/W3197798809","https://openalex.org/W3198694222","https://openalex.org/W3205788551","https://openalex.org/W4211032490","https://openalex.org/W4221146809","https://openalex.org/W4224918838","https://openalex.org/W4225590069","https://openalex.org/W4226162428","https://openalex.org/W4283031490","https://openalex.org/W4286987939","https://openalex.org/W4288099666","https://openalex.org/W4292779060","https://openalex.org/W4296068796","https://openalex.org/W4311000453","https://openalex.org/W4372259807","https://openalex.org/W4376652984","https://openalex.org/W4384662964","https://openalex.org/W4385245566","https://openalex.org/W4385822293","https://openalex.org/W4385822890","https://openalex.org/W6623517193","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6771467084","https://openalex.org/W6772383348","https://openalex.org/W6778883912","https://openalex.org/W6800875267","https://openalex.org/W6800888048","https://openalex.org/W6840815571","https://openalex.org/W6847363464","https://openalex.org/W6853006944"],"related_works":["https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2366718574","https://openalex.org/W4388696151","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2728912566","https://openalex.org/W2380471679"],"abstract_inverted_index":{"In":[0],"this":[1,47],"work,":[2],"we":[3,99],"propose":[4],"a":[5,23,32,64],"method":[6,103],"to":[7,37,52,72,104,107,126],"create":[8],"domain-sensitive":[9],"speech":[10],"recognition":[11],"models":[12],"that":[13,46,118],"utilize":[14],"textual":[15],"domain":[16,109,114],"information":[17],"by":[18,30],"conditioning":[19],"its":[20],"generation":[21],"on":[22,74,140],"given":[24],"text":[25],"prompt.":[26],"This":[27],"is":[28],"accomplished":[29],"fine-tuning":[31,106],"pre-trained,":[33],"end-to-end":[34],"model":[35,62,122,132],"(Whisper)":[36],"learn":[38],"from":[39,77],"demonstrations":[40],"with":[41,60,130],"prompt":[42,58,128],"examples.":[43],"We":[44,116],"show":[45],"ability":[48],"can":[49,123],"be":[50],"generalized":[51],"different":[53],"domains":[54],"and":[55,88],"even":[56],"various":[57,78,127],"contexts,":[59,129],"our":[61,102,119],"gaining":[63],"Word":[65],"Error":[66],"Rate":[67],"(WER)":[68],"reduction":[69,137],"of":[70,95,138],"up":[71],"33%":[73],"unseen":[75],"datasets":[76],"domains,":[79],"such":[80],"as":[81,111,113],"medical":[82,142],"conversation,":[83],"air":[84],"traffic":[85],"control":[86],"communication,":[87],"financial":[89],"meetings.":[90],"Considering":[91],"the":[92,131,134,141],"limited":[93],"availability":[94],"audio-transcript":[96],"pair":[97],"data,":[98],"further":[100],"extend":[101],"text-only":[105,120],"achieve":[108],"sensitivity":[110],"well":[112],"adaptation.":[115],"demonstrate":[117],"fine-tuned":[121],"also":[124],"attend":[125],"reaching":[133],"most":[135],"WER":[136],"29%":[139],"conversation":[143],"dataset.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}