{"id":"https://openalex.org/W4392902925","doi":"https://doi.org/10.1109/icassp48485.2024.10448264","title":"PromptASR for Contextualized ASR with Controllable Style","display_name":"PromptASR for Contextualized ASR with Controllable Style","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902925","doi":"https://doi.org/10.1109/icassp48485.2024.10448264"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100435425","display_name":"Xiaoyu Yang","orcid":"https://orcid.org/0000-0003-3437-8207"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Yang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751183","display_name":"Wei Kang","orcid":"https://orcid.org/0000-0002-5588-6342"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Kang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066643565","display_name":"Zengwei Yao","orcid":"https://orcid.org/0000-0002-2331-2387"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengwei Yao","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743978","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-3313-5473"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000368090","display_name":"Liyong Guo","orcid":"https://orcid.org/0000-0002-1805-6307"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyong Guo","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004231067","display_name":"Fangjun Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangjun Kuang","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020006167","display_name":"Na Li","orcid":"https://orcid.org/0000-0003-3246-0039"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lin","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100435425"],"corresponding_institution_ids":["https://openalex.org/I862669128"],"apc_list":null,"apc_paid":null,"fwci":3.1008,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92109371,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10536","last_page":"10540"},"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":0.9993000030517578,"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":0.9993000030517578,"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":0.7856270670890808},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7504671812057495},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.64344722032547},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6400564312934875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6341314315795898},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6240125298500061},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5911300778388977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5547590255737305},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5498952865600586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4882643222808838},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45024630427360535},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4330451190471649},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22915664315223694},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12457820773124695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856270670890808},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7504671812057495},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.64344722032547},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6400564312934875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6341314315795898},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6240125298500061},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5911300778388977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5547590255737305},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5498952865600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4882643222808838},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45024630427360535},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4330451190471649},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22915664315223694},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12457820773124695},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2022951240","https://openalex.org/W2143612262","https://openalex.org/W2219249508","https://openalex.org/W2936774411","https://openalex.org/W2962784628","https://openalex.org/W2963240019","https://openalex.org/W3008181812","https://openalex.org/W3015686596","https://openalex.org/W3160638507","https://openalex.org/W3198004110","https://openalex.org/W4205991051","https://openalex.org/W4225808286","https://openalex.org/W4226420874","https://openalex.org/W4226462878","https://openalex.org/W4283700324","https://openalex.org/W4372349774","https://openalex.org/W4384918448","https://openalex.org/W4385822246","https://openalex.org/W4387799863","https://openalex.org/W4391021457","https://openalex.org/W6688816777","https://openalex.org/W6755207826","https://openalex.org/W6847363464","https://openalex.org/W6854866820","https://openalex.org/W6857062747"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2944691285","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Prompts":[0],"are":[1,58],"crucial":[2],"to":[3,37,105,120,134,143],"large":[4],"language":[5],"models":[6],"as":[7,13,80,118],"they":[8],"provide":[9],"context":[10],"information":[11],"such":[12],"topic":[14],"or":[15],"logical":[16],"relationships.":[17],"Inspired":[18],"by":[19,64],"this,":[20],"we":[21],"propose":[22],"PromptASR,":[23],"a":[24,47,96,106],"framework":[25],"that":[26],"integrates":[27],"prompts":[28,54],"in":[29],"end-to-end":[30],"automatic":[31],"speech":[32,62],"recognition":[33,122],"(E2E":[34],"ASR)":[35],"systems":[36],"achieve":[38],"contextualized":[39],"ASR":[40,108,141],"with":[41],"controllable":[42],"style":[43,129],"of":[44,147],"transcriptions.":[45,148],"Specifically,":[46],"dedicated":[48],"text":[49,53,76,136],"encoder":[50,63,137],"encodes":[51],"the":[52,56,61,66,73,83,135,140],"and":[55,88,100,138],"encodings":[57],"injected":[59],"into":[60],"cross-attending":[65],"features":[67],"from":[68,77],"two":[69],"modalities.":[70],"When":[71],"using":[72],"ground":[74],"truth":[75],"preceding":[78],"utterances":[79],"content":[81],"prompt,":[82],"proposed":[84],"system":[85,111,142],"achieves":[86],"21.9%":[87],"6.8%":[89],"relative":[90],"word":[91],"error":[92],"rate":[93],"reductions":[94],"on":[95,124],"book":[97],"reading":[98],"dataset":[99,103],"an":[101],"in-house":[102],"compared":[104],"baseline":[107],"system.":[109],"The":[110,149],"can":[112,131],"also":[113],"take":[114],"word-level":[115],"biasing":[116],"lists":[117],"prompt":[119,130],"improve":[121],"accuracy":[123],"rare":[125],"words.":[126],"An":[127],"additional":[128],"be":[132],"given":[133],"guide":[139],"output":[144],"different":[145],"styles":[146],"code":[150],"is":[151],"available":[152],"at":[153],"icefall":[154],"<sup":[155],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[157],".":[158]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}