{"id":"https://openalex.org/W2408125366","doi":"https://doi.org/10.1109/icassp.2016.7472686","title":"Non-negative intermediate-layer DNN adaptation for a 10-KB speaker adaptation profile","display_name":"Non-negative intermediate-layer DNN adaptation for a 10-KB speaker adaptation profile","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408125366","doi":"https://doi.org/10.1109/icassp.2016.7472686","mag":"2408125366"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5047826067","display_name":"Kshitiz Kumar","orcid":"https://orcid.org/0000-0003-2728-2493"},"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":"Kshitiz Kumar","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004148430","display_name":"Chaojun Liu","orcid":"https://orcid.org/0000-0002-4676-3981"},"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":"Chaojun Liu","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","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, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047826067"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.2854,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86538563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"401","issue":null,"first_page":"5285","last_page":"5289"},"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":0.998199999332428,"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":0.9977999925613403,"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/adaptation","display_name":"Adaptation (eye)","score":0.8622108101844788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402986884117126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6756653189659119},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5196194052696228},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5060188174247742},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.46811217069625854},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4430626332759857},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14780917763710022},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07421377301216125}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.8622108101844788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402986884117126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6756653189659119},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5196194052696228},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5060188174247742},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.46811217069625854},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4430626332759857},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14780917763710022},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07421377301216125},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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":29,"referenced_works":["https://openalex.org/W26243928","https://openalex.org/W567546468","https://openalex.org/W1498436455","https://openalex.org/W1770758908","https://openalex.org/W1902027874","https://openalex.org/W1989549063","https://openalex.org/W2037740282","https://openalex.org/W2053067333","https://openalex.org/W2056738732","https://openalex.org/W2079623482","https://openalex.org/W2081709028","https://openalex.org/W2087006792","https://openalex.org/W2094147890","https://openalex.org/W2145692202","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2157711090","https://openalex.org/W2160815625","https://openalex.org/W2165880886","https://openalex.org/W2184045248","https://openalex.org/W2400108189","https://openalex.org/W2400607496","https://openalex.org/W2403307129","https://openalex.org/W2403797310","https://openalex.org/W2404620314","https://openalex.org/W6639887976","https://openalex.org/W6670225552","https://openalex.org/W6712648878","https://openalex.org/W6712702857"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W2547793174","https://openalex.org/W2132885390","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817"],"abstract_inverted_index":{"Previously":[0],"we":[1,25,49,59],"demonstrated":[2],"that":[3,111],"speaker":[4,31],"adaptation":[5,32,53,63,81,124],"of":[6,17,35,40,69,136],"acoustic":[7],"models":[8],"(AM)":[9],"can":[10],"provide":[11],"significant":[12],"improvement":[13],"in":[14,29,90,133],"the":[15,38,105,115,134,147],"accuracy":[16],"large-scale":[18],"speech":[19],"recognition":[20],"systems.":[21],"In":[22],"this":[23,76],"work":[24,77],"discuss":[26,100],"numerous":[27],"challenges":[28],"scaling":[30],"to":[33,96,103,126],"millions":[34],"speakers,":[36],"where":[37],"size":[39,135],"speaker-dependent":[41],"(SD)":[42],"parameters":[43,117],"is":[44],"a":[45,61,65,83],"critical":[46],"challenge.":[47],"Subsequently,":[48],"formulate":[50],"an":[51,91],"intermediate-layer":[52],"framework":[54],"for":[55,64,120],"adaptation,":[56],"upon":[57],"which":[58],"build":[60],"non-negative":[62,70,80,94,106],"very":[66],"sparse":[67],"set":[68],"SD":[71,107,116,137],"parameters.":[72,108],"We":[73,98,109],"further":[74],"improve":[75],"with,":[78],"(a)":[79],"with":[82],"small-positive":[84,88],"threshold,":[85],"(b)":[86],"setting":[87],"weights":[89],"already":[92],"trained":[93],"model":[95],"zero.":[97],"also":[99],"effective":[101],"methods":[102,113],"store":[104],"show":[110],"our":[112,121],"reduce":[114],"from":[118],"86KB":[119],"previous":[122],"best":[123],"approach":[125],"8.8KB,":[127],"thus":[128],"about":[129],"90%":[130],"relative":[131],"reduction":[132],"parameters,":[138],"and":[139],"still":[140],"retain":[141],"10+%":[142],"word-error-rate-relative":[143],"(WERR)":[144],"gain":[145],"over":[146],"baseline":[148],"speaker-independent":[149],"(SI)":[150],"model.":[151]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}