乐胖代购免代理版

{"id":"https://openalex.org/W2401442364","doi":"https://doi.org/10.1109/icassp.2016.7472642","title":"Discriminatively trained joint speaker and environment representations for adaptation of deep neural network acoustic models","display_name":"Discriminatively trained joint speaker and environment representations for adaptation of deep neural network acoustic models","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2401442364","doi":"https://doi.org/10.1109/icassp.2016.7472642","mag":"2401442364"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5089806443","display_name":"Maofan Yin","orcid":"https://orcid.org/0009-0006-2717-8150"},"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":"Maofan Yin","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058653260","display_name":"Sunil Sivadas","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sunil Sivadas","raw_affiliation_strings":["Human Language Technology Lab., Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Lab., Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"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":"Kai Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Human Language Technology Lab., Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Lab., Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.227,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":6,"citation_normalized_percentile":{"value":0.481816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":84},"biblio":{"volume":"313","issue":null,"first_page":"5065","last_page":"5069"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition Technology","score":0.9999,"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 Technology","score":0.9999,"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 Enhancement Techniques","score":0.998,"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":"Audio Signal Classification and Analysis","score":0.9967,"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/normalization","display_name":"Normalization (sociology)","score":0.76087546},{"id":"https://openalex.org/keywords/environmental-sound-recognition","display_name":"Environmental Sound Recognition","score":0.589716},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"Acoustic Modeling","score":0.569583},{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"Audio-Visual Speech Recognition","score":0.565252},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"Speaker Diarization","score":0.555976},{"id":"https://openalex.org/keywords/automatic-speech-recognition","display_name":"Automatic Speech Recognition","score":0.553686},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.47030064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764821},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.76087546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.68387616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57942665},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5526458},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.53016806},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.47030064},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45762572},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4569938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41345406},{"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.74,"display_name":"Reduced inequalities"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":19,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1513820424","https://openalex.org/W1524333225","https://openalex.org/W1592672653","https://openalex.org/W1985371235","https://openalex.org/W2002342963","https://openalex.org/W2017637319","https://openalex.org/W2046056978","https://openalex.org/W2048526313","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2099621636","https://openalex.org/W2100495367","https://openalex.org/W2107638917","https://openalex.org/W2137630452","https://openalex.org/W2150769028","https://openalex.org/W2403307129","https://openalex.org/W2913340405"],"related_works":["https://openalex.org/W4313854686","https://openalex.org/W4297807400","https://openalex.org/W3044757496","https://openalex.org/W2249138175","https://openalex.org/W2105635394","https://openalex.org/W2087669554","https://openalex.org/W2067459736","https://openalex.org/W1911592522","https://openalex.org/W153239700","https://openalex.org/W1491159402"],"abstract_inverted_index":{"A":[0],"recent":[1],"trend":[2],"in":[3,24],"normalization":[4,93],"of":[5,27,44,80,87,94,100,124,164,185],"factors":[6,47,82],"extraneous":[7,46],"to":[8,15,20,75,136,153,160],"a":[9,115,120,130,133,165],"speech":[10],"recognition":[11],"task":[12],"has":[13],"been":[14],"explicitly":[16],"introduce":[17],"features":[18,61,140],"related":[19],"the":[21,25,39,58,81,84,95,138,162,186],"unwanted":[22],"variability":[23],"training":[26,40,129],"Deep":[28],"Neural":[29],"Networks":[30],"(DNN).":[31],"Typically,":[32],"this":[33,111,155],"is":[34,74,152],"done":[35],"by":[36,128,146],"either":[37,105],"perturbing":[38],"set":[41],"with":[42,62,132],"models":[43],"these":[45,101],"such":[48,65],"as":[49,66],"vocal":[50],"tract":[51],"length":[52],"and":[53,89,126,143,174],"environmental":[54],"noise":[55,68],"or":[56,107],"augmenting":[57],"conventional":[59],"spectral":[60],"auxiliary":[63],"information":[64],"i-vector,":[67],"spectrum,":[69],"etc.":[70],"Another":[71,150],"emerging":[72],"approach":[73,117],"derive":[76],"low":[77],"dimensional":[78],"representations":[79,194],"from":[83],"hidden":[85],"layers":[86],"DNN":[88],"use":[90],"it":[91],"for":[92,118],"acoustic":[96],"model.":[97],"Almost":[98],"all":[99],"approaches":[102],"focus":[103],"on":[104,180],"speaker":[106,142,172],"environment":[108,127,144],"normalization.":[109],"In":[110],"paper":[112],"we":[113],"propose":[114],"novel":[116],"estimating":[119],"compact":[121,156,191],"joint":[122,192],"representation":[123,157],"speakers":[125],"DNN,":[131],"bottleneck":[134],"layer,":[135],"classify":[137],"i-vector":[139,163,173],"into":[141,168],"labels":[145],"Multi-Task":[147],"Learning":[148],"(MTL).":[149],"novelty":[151],"learn":[154],"while":[158],"learning":[159],"map":[161],"noisy":[166],"utterance":[167],"its":[169],"corresponding":[170],"clean":[171],"noise-only":[175],"i-vector.":[176],"Experiments":[177],"were":[178],"conducted":[179],"an":[181],"artificially":[182],"noise-corrupted":[183],"version":[184],"WSJ":[187],"corpus.":[188],"The":[189],"proposed":[190],"speaker-environment":[193],"show":[195],"promising":[196],"gains.":[197]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2401442364","counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2024-11-30T19:49:56.340541","created_date":"2016-06-24"}