{"id":"https://openalex.org/W1993409002","doi":"https://doi.org/10.1109/icassp.2013.6639211","title":"Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code","display_name":"Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1993409002","doi":"https://doi.org/10.1109/icassp.2013.6639211","mag":"1993409002"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":["Department of Computer Science and Engineering, York University, Toronto, ONT, Canada","Department of Computer Science and Engineering York University, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, York University, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"Department of Computer Science and Engineering York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, York University, Toronto, ONT, Canada","Department of Computer Science and Engineering York University, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, York University, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"Department of Computer Science and Engineering York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":224,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7942","last_page":"7946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9912999868392944,"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":0.984000027179718,"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/speech-recognition","display_name":"Speech recognition","score":0.814112663269043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8116003274917603},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7898637652397156},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6912323832511902},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6377061605453491},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6228599548339844},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6226296424865723},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6075388193130493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4233071804046631},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4177253842353821},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3937605917453766}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.814112663269043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116003274917603},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7898637652397156},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6912323832511902},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6377061605453491},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6228599548339844},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6226296424865723},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6075388193130493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4233071804046631},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4177253842353821},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3937605917453766},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.702.9599","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.702.9599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.yorku.ca/%7Eossama/pub/adaptation.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W26405188","https://openalex.org/W185613617","https://openalex.org/W1513862252","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2052248915","https://openalex.org/W2063689849","https://openalex.org/W2076794394","https://openalex.org/W2077804127","https://openalex.org/W2080005694","https://openalex.org/W2100969003","https://openalex.org/W2106119541","https://openalex.org/W2121981798","https://openalex.org/W2144792281","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2160306971","https://openalex.org/W2394932179","https://openalex.org/W2397860787","https://openalex.org/W6601083597","https://openalex.org/W6607553906","https://openalex.org/W6630673164"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2501000458","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853"],"abstract_inverted_index":{"In":[0,72,124],"this":[1,73,125,152],"paper,":[2],"we":[3],"propose":[4],"a":[5,23,27,87,93,101,110,127,165,172,187,195],"new":[6,102,111],"fast":[7,174],"speaker":[8,41,56,64,84,95,103,112,129,135,159,183],"adaptation":[9,19,30,60,77,139,175,191],"method":[10,20,49,153],"for":[11,33,133,181,221],"the":[12,68,75,115,137,144,156,177],"hybrid":[13,178],"NN-HMM":[14],"speech":[15],"recognition":[16],"model.":[17],"The":[18,46,148],"depends":[21],"on":[22,67,185,200],"joint":[24,47],"learning":[25,109],"of":[26,81,151,158,176,190],"large":[28,138],"generic":[29,88],"neural":[31],"network":[32],"all":[34,51],"speakers":[35],"as":[36,38],"well":[37],"multiple":[39],"small":[40,94,188],"codes":[42,65,160],"(one":[43],"per":[44],"speaker).":[45],"training":[48,52,146],"uses":[50],"data":[53,192],"along":[54],"with":[55],"labels":[57],"to":[58,100,170],"update":[59],"NN":[61,78,122,140],"weights":[62],"and":[63],"based":[66,184],"standard":[69],"back-propagation":[70,117],"algorithm.":[71],"way,":[74],"learned":[76,132,142],"is":[79,97,131,141,154,161,168],"capable":[80],"transforming":[82],"each":[83,134,182],"features":[85],"into":[86],"speaker-independent":[89],"feature":[90],"space":[91],"when":[92],"code":[96,113,130],"given.":[98],"Adaptation":[99],"can":[104,206],"be":[105],"simply":[106],"done":[107],"by":[108,216],"using":[114,217],"same":[116],"algorithm":[118],"without":[119],"changing":[120],"any":[121],"weights.":[123],"method,":[126],"separate":[128],"while":[136],"from":[143],"whole":[145],"set.":[147],"main":[149],"advantage":[150],"that":[155,204],"size":[157],"very":[162,173],"small.":[163],"As":[164],"result,":[166],"it":[167,205],"possible":[169],"conduct":[171],"NN/HMM":[179],"model":[180],"only":[186,218],"amount":[189],"(i.e.,":[193],"just":[194],"few":[196],"utterances).":[197],"Experimental":[198],"results":[199],"TIMIT":[201],"have":[202],"shown":[203],"achieve":[207],"over":[208],"10%":[209],"relative":[210],"reduction":[211],"in":[212],"phone":[213],"error":[214],"rate":[215],"seven":[219],"utterances":[220],"adaptation.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":41},{"year":2015,"cited_by_count":28},{"year":2014,"cited_by_count":26},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}