{"id":"https://openalex.org/W1595761392","doi":"https://doi.org/10.1109/icassp.2015.7178833","title":"Unsupervised speaker adaptation of deep neural network based on the combination of speaker codes and singular value decomposition for speech recognition","display_name":"Unsupervised speaker adaptation of deep neural network based on the combination of speaker codes and singular value decomposition for speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1595761392","doi":"https://doi.org/10.1109/icassp.2015.7178833","mag":"1595761392"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5083184776","display_name":"Shaofei Xue","orcid":"https://orcid.org/0000-0001-6199-7965"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Xue","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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 Electrical Engineering and Computer Science, York University, Toronto, Canada","Department of Electrical Engineering & Computer Science, York University, Toronto, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, York University, Toronto, CANADA","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100349220","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-8857-6677"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Liu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"4555","last_page":"4559"},"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":0.9973999857902527,"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":0.9944999814033508,"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":0.7613886594772339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7137151956558228},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6871428489685059},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6170755624771118},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.562751293182373},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5397151112556458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5030938982963562},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5002150535583496},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.49043771624565125},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4605085253715515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4523979425430298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613886594772339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7137151956558228},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6871428489685059},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6170755624771118},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.562751293182373},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5397151112556458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5030938982963562},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5002150535583496},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.49043771624565125},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4605085253715515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4523979425430298},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1513862252","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2016084804","https://openalex.org/W2036351241","https://openalex.org/W2046899276","https://openalex.org/W2052248915","https://openalex.org/W2058641082","https://openalex.org/W2063689849","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2081884280","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2100969003","https://openalex.org/W2112021726","https://openalex.org/W2121981798","https://openalex.org/W2146871184","https://openalex.org/W2160306971","https://openalex.org/W2161591461","https://openalex.org/W2294543795","https://openalex.org/W2403731734","https://openalex.org/W2952899695","https://openalex.org/W3162418253","https://openalex.org/W6630673164","https://openalex.org/W6654315276","https://openalex.org/W6670225552","https://openalex.org/W6671190587","https://openalex.org/W6676587989","https://openalex.org/W6683826617","https://openalex.org/W6696912008"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Recently,":[0],"we":[1,93,126,166],"have":[2,94,167,187],"proposed":[3,174],"a":[4,83,97,128,147,155],"general":[5],"adaptation":[6,23,88,171],"scheme":[7],"for":[8,62,193],"deep":[9],"neural":[10],"network":[11],"based":[12,27,72],"on":[13,28],"discriminant":[14],"condition":[15,47],"codes":[16,116,141],"and":[17,102,117,142,160,197],"applied":[18],"it":[19,190],"to":[20,95,105,138,145],"supervised":[21],"speaker":[22,53,60,70,99,115,140,157,170],"in":[24,54,77,136,176,181,199],"speech":[25,179],"recognition":[26,180],"either":[29],"frame-level":[30],"cross-entropy":[31],"or":[32],"sequence-level":[33],"maximum":[34],"mutual":[35],"information":[36],"training":[37],"criterion":[38],"[1,":[39],"2,":[40],"3,":[41],"4].":[42],"In":[43,123],"this":[44,124],"case,":[45],"each":[46],"code":[48,61,71,100,158],"is":[49,57,90,191],"associated":[50],"with":[51,154,172],"one":[52],"data,":[55],"which":[56],"thus":[58],"called":[59],"convenience.":[63],"Our":[64],"previous":[65],"work":[66],"has":[67],"shown":[68,188],"that":[69,189],"methods":[73],"are":[74,120],"quite":[75],"effective":[76,192],"adapting":[78,200],"DNNs":[79],"even":[80],"when":[81],"only":[82],"very":[84,121],"small":[85],"amount":[86],"of":[87,114],"data":[89],"available.":[91],"However,":[92],"use":[96],"large":[98,177,201],"size":[101,159],"complex":[103],"processes":[104],"obtain":[106,146],"the":[107,173,182],"best":[108],"ASR":[109,149],"performance":[110,150],"since":[111],"good":[112],"initializations":[113,196],"connection":[118,143],"weights":[119,144],"important.":[122],"paper,":[125],"propose":[127],"method":[129,175],"using":[130],"singular":[131],"value":[132],"decomposition":[133],"(SVD)":[134],"as":[135,151],"[5]":[137],"initialize":[139],"comparable":[148],"before":[152],"but":[153],"smaller":[156],"much":[161],"less":[162],"computation":[163],"complexity.":[164],"Meanwhile,":[165],"evaluated":[168],"unsupervised":[169],"vocabulary":[178],"Switchboard":[183],"task.":[184],"Experimental":[185],"results":[186],"providing":[194],"well":[195],"suitable":[198],"DNN":[202],"models.":[203]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}