{"id":"https://openalex.org/W2799674897","doi":"https://doi.org/10.1109/icassp.2018.8461553","title":"Domain and Speaker Adaptation for Cortana Speech Recognition","display_name":"Domain and Speaker Adaptation for Cortana Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2799674897","doi":"https://doi.org/10.1109/icassp.2018.8461553","mag":"2799674897"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yong Zhao","raw_affiliation_strings":["Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785327","display_name":"Shi-Xiong Zhang","orcid":"https://orcid.org/0009-0007-7803-2407"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shixiong Zhang","raw_affiliation_strings":["Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430197","display_name":"Liping Chen","orcid":"https://orcid.org/0000-0003-1902-0215"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liping Chen","raw_affiliation_strings":["Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100702071"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.0948,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93188351,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5984","last_page":"5988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9991999864578247,"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":0.7751904129981995},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6450013518333435},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6006008982658386},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5766609311103821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.521522581577301},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4322822093963623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4054572582244873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3606119751930237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08367416262626648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751904129981995},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6450013518333435},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6006008982658386},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5766609311103821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.521522581577301},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4322822093963623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4054572582244873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3606119751930237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08367416262626648},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W143957211","https://openalex.org/W567546468","https://openalex.org/W1513862252","https://openalex.org/W1770758908","https://openalex.org/W1984541135","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2005708641","https://openalex.org/W2010362084","https://openalex.org/W2015633636","https://openalex.org/W2046056978","https://openalex.org/W2056738732","https://openalex.org/W2076794394","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2094147890","https://openalex.org/W2114925438","https://openalex.org/W2117239706","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2181607856","https://openalex.org/W2293634267","https://openalex.org/W2294543795","https://openalex.org/W2296748324","https://openalex.org/W2394882406","https://openalex.org/W2396384435","https://openalex.org/W2402476435","https://openalex.org/W2403524927","https://openalex.org/W2407146636","https://openalex.org/W2508162385","https://openalex.org/W2514740276","https://openalex.org/W2680270903","https://openalex.org/W2695252763","https://openalex.org/W2735006420","https://openalex.org/W2749659773","https://openalex.org/W2962894366","https://openalex.org/W2963381607","https://openalex.org/W2964182776","https://openalex.org/W4235765578","https://openalex.org/W6603403951","https://openalex.org/W6615969787","https://openalex.org/W6629815555","https://openalex.org/W6638079348","https://openalex.org/W6639822467","https://openalex.org/W6646550796","https://openalex.org/W6646979388","https://openalex.org/W6647755045","https://openalex.org/W6651673773","https://openalex.org/W6652979549","https://openalex.org/W6654250109","https://openalex.org/W6662018943","https://openalex.org/W6664430995","https://openalex.org/W6669760234","https://openalex.org/W6670225552","https://openalex.org/W6672565315","https://openalex.org/W6674052071","https://openalex.org/W6677390740","https://openalex.org/W6677632922","https://openalex.org/W6681513673","https://openalex.org/W6683263180","https://openalex.org/W6696912008","https://openalex.org/W6696934422","https://openalex.org/W6697318756","https://openalex.org/W6711879727","https://openalex.org/W6712195726","https://openalex.org/W6713141481","https://openalex.org/W6713292810","https://openalex.org/W6713806900","https://openalex.org/W6739935953","https://openalex.org/W6739965251"],"related_works":["https://openalex.org/W2385242602","https://openalex.org/W2043069908","https://openalex.org/W1607020250","https://openalex.org/W2021573333","https://openalex.org/W2893763841","https://openalex.org/W1921130144","https://openalex.org/W2035938076","https://openalex.org/W2370281303","https://openalex.org/W2170807154","https://openalex.org/W2778699561"],"abstract_inverted_index":{"Voice":[0],"assistant":[1],"represents":[2],"one":[3],"of":[4,33,55,70,76,127],"the":[5,44,52,68,83,100,105,109,113,121,142,150,154,164],"most":[6],"popular":[7],"and":[8,74,153],"important":[9],"scenarios":[10],"for":[11,87],"speech":[12],"recognition.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,37,80],"propose":[18],"two":[19],"adaptation":[20,41,102,148],"approaches":[21,140],"to":[22,63,66,103],"customize":[23],"a":[24,117],"multi-style":[25],"well-trained":[26],"acoustic":[27],"model":[28,85],"towards":[29],"its":[30],"subsidiary":[31],"domain":[32,88,123],"Cortana":[34,133],"assistant.":[35],"First,":[36],"present":[38],"anchor-based":[39,147],"speaker":[40,45],"by":[42],"extracting":[43],"information,":[46],"i-vector":[47],"or":[48],"d-vector":[49,152],"embeddings,":[50],"from":[51,108],"anchor":[53,59,128,151],"segments":[54],"\u2018Hey":[56],"Cortana\u2019.":[57],"The":[58,146],"embeddings":[60],"are":[61],"mapped":[62],"layer-wise":[64],"parameters":[65,86],"control":[67],"transformations":[69],"both":[71,139],"weight":[72],"matrices":[73],"biases":[75],"multiple":[77],"layers.":[78],"Second,":[79],"directly":[81],"update":[82],"existing":[84],"adaptation.":[89],"We":[90],"demonstrate":[91],"that":[92,138],"prior":[93,155],"distribution":[94],"should":[95],"be":[96],"updated":[97],"along":[98],"with":[99],"network":[101],"compensate":[104],"label":[106],"bias":[107],"development":[110],"data.":[111],"Updating":[112],"priors":[114],"may":[115],"have":[116],"significant":[118],"impact":[119],"when":[120],"target":[122],"features":[124],"high":[125],"occurrence":[126],"words.":[129],"Experiments":[130],"on":[131],"Hey":[132],"desktop":[134],"test":[135],"set":[136],"show":[137],"improve":[141],"recognition":[143],"accuracy":[144],"significantly.":[145],"using":[149],"interpolation":[156],"achieves":[157],"32%":[158],"relative":[159],"reduction":[160],"in":[161],"WER":[162],"over":[163],"generic":[165],"model.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}