{"id":"https://openalex.org/W2402922286","doi":"https://doi.org/10.1109/icassp.2016.7472783","title":"Integrated adaptation with multi-factor joint-learning for far-field speech recognition","display_name":"Integrated adaptation with multi-factor joint-learning for far-field speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2402922286","doi":"https://doi.org/10.1109/icassp.2016.7472783","mag":"2402922286"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472783","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/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","Engineering Department, Cambridge University, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667381","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0002-4723-0044"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["MIT CSAIL, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL, Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100341993"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":6.8556,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96890672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"5770","last_page":"5774"},"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":0.9998999834060669,"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":0.9994000196456909,"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":0.8268512487411499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.710361123085022},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6368433237075806},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.621249258518219},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6060581803321838},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4978330135345459},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48915937542915344},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.48729002475738525},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47634246945381165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47494959831237793},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44298428297042847},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43876147270202637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4211207628250122},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06913161277770996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268512487411499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.710361123085022},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6368433237075806},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.621249258518219},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6060581803321838},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4978330135345459},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48915937542915344},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.48729002475738525},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47634246945381165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47494959831237793},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44298428297042847},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43876147270202637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4211207628250122},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06913161277770996},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472783","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1006777433","https://openalex.org/W1489048302","https://openalex.org/W1499999342","https://openalex.org/W1524333225","https://openalex.org/W1592672653","https://openalex.org/W1665196592","https://openalex.org/W1943324956","https://openalex.org/W1973669708","https://openalex.org/W2022608894","https://openalex.org/W2037740282","https://openalex.org/W2046056978","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2080921589","https://openalex.org/W2107638917","https://openalex.org/W2112021726","https://openalex.org/W2117239706","https://openalex.org/W2119203697","https://openalex.org/W2137630452","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2394932179","https://openalex.org/W2403307129","https://openalex.org/W2403553999","https://openalex.org/W2406778302","https://openalex.org/W2616139854","https://openalex.org/W6631362777","https://openalex.org/W6680394064","https://openalex.org/W6686045668","https://openalex.org/W6713287686","https://openalex.org/W6713597360","https://openalex.org/W6738021889"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W2370205415","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W2030332364","https://openalex.org/W2005459225","https://openalex.org/W2061937230","https://openalex.org/W2189081180"],"abstract_inverted_index":{"Although":[0],"great":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"in":[6,16,82,95,107],"automatic":[7],"speech":[8,48],"recognition":[9,44],"(ASR),":[10],"significant":[11],"performance":[12],"degradation":[13],"still":[14],"exists":[15],"distant":[17,47,146],"talking":[18],"scenarios":[19],"due":[20],"to":[21,41,73,89],"significantly":[22,156],"lower":[23],"signal":[24],"power.":[25],"In":[26,77],"this":[27],"paper,":[28],"a":[29],"novel":[30,129],"adaptation":[31,35],"framework,":[32],"named":[33],"integrated":[34,67],"with":[36,171],"multi-factor":[37],"joint-learning,":[38],"is":[39],"proposed":[40,153],"improve":[42,74,90],"the":[43,69,79,83,91,98,102,108,119,143,152,172,189,192],"accuracy":[45],"for":[46,136],"recognition.":[49],"We":[50],"explore":[51],"and":[52,56,111,139,162,182,194],"extract":[53],"speaker,":[54],"phone":[55],"environment":[57],"factor":[58,92,112,137],"representations":[59],"using":[60,191],"deep":[61],"neural":[62],"networks":[63],"(DNNs),":[64],"which":[65,94],"are":[66,87,115],"into":[68],"main":[70,84],"ASR":[71,85,99,109],"DNN":[72,86,110],"classification":[75],"accuracy.":[76],"addition,":[78],"hidden":[80],"activations":[81],"used":[88],"extraction,":[93],"turn":[96],"helps":[97],"DNN.":[100],"All":[101],"model":[103],"parameters,":[104],"including":[105],"those":[106],"extractor":[113],"DNNs,":[114],"jointly":[116],"optimized":[117],"under":[118],"multi-task":[120],"learning":[121],"framework.":[122],"Further":[123],"more,":[124],"unlike":[125],"prior":[126],"techniques,":[127],"our":[128],"approach":[130],"requires":[131],"no":[132],"explicit":[133],"separate":[134],"stages":[135],"extraction":[138],"adaptation.":[140,174],"Experiments":[141],"on":[142,186],"AMI":[144],"single":[145],"microphone":[147],"(SDM)":[148],"task":[149],"show":[150],"that":[151],"architecture":[154],"can":[155,165],"reduce":[157],"word":[158],"error":[159],"rate":[160],"(WER)":[161],"additional":[163],"improvement":[164],"be":[166],"achieved":[167],"by":[168],"combining":[169],"it":[170],"i-vector":[173],"Our":[175],"best":[176],"configuration":[177],"obtained":[178],"more":[179],"than":[180],"15%":[181],"10%":[183],"relative":[184],"reduction":[185],"WER":[187],"over":[188],"baselines":[190],"SDM":[193],"close-talk":[195],"data":[196],"generated":[197],"alignments,":[198],"respectively.":[199]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}