{"id":"https://openalex.org/W3015216127","doi":"https://doi.org/10.1109/icassp40776.2020.9053545","title":"Acoustic Model Adaptation for Presentation Transcription and Intelligent Meeting Assistant Systems","display_name":"Acoustic Model Adaptation for Presentation Transcription and Intelligent Meeting Assistant Systems","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015216127","doi":"https://doi.org/10.1109/icassp40776.2020.9053545","mag":"3015216127"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100764456","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-0575-0156"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100764456"],"corresponding_institution_ids":["https://openalex.org/I4210105678"],"apc_list":null,"apc_paid":null,"fwci":0.9279,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79868896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7394","last_page":"7398"},"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":0.9979000091552734,"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":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.7877757549285889},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6204929351806641},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5840897560119629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5545307397842407},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5179518461227417},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5131369233131409},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4721158742904663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4003807008266449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877757549285889},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6204929351806641},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5840897560119629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5545307397842407},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5179518461227417},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5131369233131409},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4721158742904663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4003807008266449},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W567546468","https://openalex.org/W1509793305","https://openalex.org/W1513862252","https://openalex.org/W1571447047","https://openalex.org/W1961429348","https://openalex.org/W1979651826","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2056738732","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2100772283","https://openalex.org/W2100969003","https://openalex.org/W2143860348","https://openalex.org/W2146871184","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2291282366","https://openalex.org/W2395655916","https://openalex.org/W2397860787","https://openalex.org/W2399832792","https://openalex.org/W2400607496","https://openalex.org/W2508162385","https://openalex.org/W2802248956","https://openalex.org/W2889182644","https://openalex.org/W2889374926","https://openalex.org/W2939173691","https://openalex.org/W2964182776","https://openalex.org/W3008283340","https://openalex.org/W3125118953","https://openalex.org/W6615969787","https://openalex.org/W6630673164","https://openalex.org/W6634371499","https://openalex.org/W6639822467","https://openalex.org/W6697112914","https://openalex.org/W6712213709","https://openalex.org/W6712756720","https://openalex.org/W6724991294"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W2770593030","https://openalex.org/W3118585974","https://openalex.org/W3154990682","https://openalex.org/W200981350","https://openalex.org/W4386907265","https://openalex.org/W2058752985","https://openalex.org/W2293740626","https://openalex.org/W1499712254","https://openalex.org/W2915347927"],"abstract_inverted_index":{"We":[0,18],"present":[1],"our":[2,132,163],"solution":[3,107],"for":[4],"unsupervised":[5],"rapid":[6,172],"speaker":[7,173],"adaptation":[8,26,30,39,56,100,116,174],"in":[9,47],"a":[10,65,98,124,128,148,167,176],"state-of-art":[11,177],"presentation":[12,125],"and":[13,50,89,120,127,138],"intelligent":[14],"meeting":[15,129],"transcription":[16,126,130],"system.":[17,179],"adopt":[19],"the":[20,29,35,44,60,82,105,110,160],"Kullback-Leibler":[21],"(KL)":[22],"divergence":[23],"regularized":[24,112],"model":[25,151],"paradigm.":[27],"For":[28],"architecture,":[31],"we":[32,63,86],"found":[33],"that":[34],"linear":[36,113],"projection":[37,114],"layer":[38,115],"yields":[40,135],"competitive":[41],"performance":[42],"with":[43,117],"additional":[45],"benefit":[46],"its":[48],"simplicity":[49],"robustness":[51],"to":[52,75,96],"small":[53],"amount":[54],"of":[55,109,155,162],"data.":[57],"To":[58,80,159],"address":[59],"imperfect":[61],"supervision,":[62],"use":[64],"supervision":[66],"committee":[67],"formed":[68],"by":[69],"multiple":[70],"systems":[71],"or":[72],"single-system":[73],"n-best":[74],"mask":[76],"possibly":[77],"mislabeled":[78],"frames.":[79],"relieve":[81],"data":[83,93,101,121],"sparsity":[84],"issue,":[85],"apply":[87],"noise":[88],"speaking":[90],"rate":[91,144],"perturbation":[92],"augmentation":[94],"techniques":[95],"create":[97],"richer":[99],"set.":[102],"In":[103],"summary,":[104],"proposed":[106,133],"consists":[108],"KL-divergence":[111],"frame":[118],"masking":[119],"augmentation.":[122],"On":[123],"task,":[131],"methodology":[134],"7.3":[136],"%":[137,140],"7.9":[139],"relative":[141],"word":[142],"error":[143],"(WER)":[145],"reduction":[146],"against":[147],"strong":[149],"baseline":[150],"trained":[152],"from":[153],"tens":[154],"thousand":[156],"hour":[157],"speech.":[158],"best":[161],"knowledge,":[164],"this":[165],"is":[166],"first":[168],"reported":[169],"work":[170],"on":[171,175],"production":[178]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}