{"id":"https://openalex.org/W2055842011","doi":"https://doi.org/10.1109/icassp.2014.6854822","title":"Deep neural network trained with speaker representation for speaker normalization","display_name":"Deep neural network trained with speaker representation for speaker normalization","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2055842011","doi":"https://doi.org/10.1109/icassp.2014.6854822","mag":"2055842011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5033437280","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0002-3122-5881"},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Nuance Communications","Nuance Communication, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]},{"raw_affiliation_string":"Nuance Communication, Burlington, MA, USA","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036974323","display_name":"Aanchan Mohan","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Aanchan Mohan","raw_affiliation_strings":["McGill University","McGill University, Montreal, QC, Canada.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, Montreal, QC, Canada.;","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077077136","display_name":"Richard C. Rose","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard C. Rose","raw_affiliation_strings":["McGill University","McGill University, Montreal, QC, Canada.;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, Montreal, QC, Canada.;","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102725787","display_name":"Chengyuan Ma","orcid":"https://orcid.org/0000-0001-5126-5883"},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Chengyuan Ma","raw_affiliation_strings":["Nuance Communications","Nuance Communication, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]},{"raw_affiliation_string":"Nuance Communication, Burlington, MA, USA","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6329","last_page":"6333"},"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":0.9987999796867371,"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":0.9950000047683716,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7812097072601318},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7710149884223938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7432551980018616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7432364225387573},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7150558829307556},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6377361416816711},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5836442112922668},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5668069124221802},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5647760629653931},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5636357665061951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49959397315979004},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.497104674577713}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7812097072601318},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7710149884223938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7432551980018616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432364225387573},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7150558829307556},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6377361416816711},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5836442112922668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5668069124221802},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5647760629653931},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5636357665061951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49959397315979004},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.497104674577713},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W137106866","https://openalex.org/W1513862252","https://openalex.org/W1599512239","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2022608894","https://openalex.org/W2035424729","https://openalex.org/W2039671743","https://openalex.org/W2062227835","https://openalex.org/W2080005694","https://openalex.org/W2105099419","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2165712214","https://openalex.org/W2184045248","https://openalex.org/W2295914911","https://openalex.org/W2403731734","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2162158162","https://openalex.org/W2162582511","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141"],"abstract_inverted_index":{"A":[0],"method":[1,22,139],"for":[2,14,32],"speaker":[3,99,123,132,150],"normalization":[4],"in":[5,25,70,112],"deep":[6],"neural":[7],"network":[8],"(DNN)":[9],"based":[10,34,58,83,117,131],"discriminative":[11],"feature":[12,39],"estimation":[13],"automatic":[15],"speech":[16],"recognition":[17],"(ASR)":[18],"is":[19,23,86,110,135],"presented.":[20],"This":[21],"applied":[24],"the":[26,42,96,106,137,142,148],"context":[27],"of":[28,98,105],"a":[29,50],"DNN":[30,118],"configured":[31],"auto-encoder":[33],"low":[35],"dimensional":[36],"bottleneck":[37],"(AE-BN)":[38],"extraction":[40],"where":[41,115],"derived":[43,127],"features":[44,63],"are":[45,64,120,126],"used":[46],"as":[47],"input":[48],"to":[49,66,78,147],"continuous":[51],"Gaussian":[52],"density":[53],"hidden":[54],"Markov":[55],"model":[56],"(HMM/GMM)":[57],"ASR":[59,71],"decoder.":[60],"While":[61],"AE-BN":[62,152],"known":[65],"provide":[67],"significant":[68],"reduction":[69],"word":[72],"error":[73],"rate":[74],"(WER)":[75],"with":[76,122],"respect":[77],"more":[79],"conventional":[80],"spectral":[81],"magnitude":[82],"features,":[84],"there":[85],"no":[87],"general":[88],"agreement":[89],"on":[90],"how":[91],"these":[92],"networks":[93],"can":[94],"reduce":[95,141],"impact":[97],"variability":[100],"by":[101,144],"incorporating":[102],"prior":[103],"knowledge":[104],"speaker.":[107],"An":[108],"approach":[109],"presented":[111],"this":[113],"paper":[114],"spectrum":[116],"inputs":[119,124],"augmented":[121],"that":[125],"from":[128],"separate":[129],"regression":[130],"transformations.":[133],"It":[134],"shown":[136],"proposed":[138],"could":[140],"WER":[143],"3%":[145],"relative":[146],"best":[149],"adapted":[151],"CDHMM":[153],"system.":[154]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}