{"id":"https://openalex.org/W2407146636","doi":"https://doi.org/10.21437/interspeech.2015-658","title":"SVD-based universal DNN modeling for multiple scenarios","display_name":"SVD-based universal DNN modeling for multiple scenarios","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2407146636","doi":"https://doi.org/10.21437/interspeech.2015-658","mag":"2407146636"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-658","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5022890229","display_name":"Changliang Liu","orcid":"https://orcid.org/0009-0005-8201-0871"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Changliang Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022890229"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7258,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89206104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3269","last_page":"3273"},"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":0.9998000264167786,"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":0.9997000098228455,"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":0.8107376098632812},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.7229253053665161},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.529900848865509},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5007545948028564},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4803546667098999},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4625365734100342},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42239877581596375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31748706102371216},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20449021458625793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107376098632812},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.7229253053665161},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.529900848865509},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5007545948028564},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4803546667098999},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4625365734100342},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42239877581596375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31748706102371216},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20449021458625793},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-658","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1555696814","https://openalex.org/W1984541135","https://openalex.org/W1993882792","https://openalex.org/W2013598660","https://openalex.org/W2056738732","https://openalex.org/W2058641082","https://openalex.org/W2076794394","https://openalex.org/W2080400971","https://openalex.org/W2125964738","https://openalex.org/W2136439176","https://openalex.org/W2294543795","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2964138484"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,82,143],"scenarios":[2,37,63,109,149],"(aka":[3],"tasks)":[4],"differ":[5],"from":[6,107],"each":[7,132],"other":[8],"in":[9,28,164],"acoustic":[10,12,20,59,169],"transducers,":[11],"environments,":[13],"and":[14,89,135,150],"speaking":[15],"style":[16],"etc.":[17],"Building":[18],"one":[19,25],"model":[21,60,183],"per":[22],"task":[23],"is":[24,184],"common":[26],"practice":[27],"industry.":[29],"However,":[30],"this":[31,94],"limits":[32],"training":[33],"data":[34,68,77,106,178],"sharing":[35],"across":[36],"thus":[38],"may":[39],"not":[40],"give":[41],"highest":[42],"possible":[43],"accuracy.":[44],"Based":[45],"on":[46,129,175],"the":[47,67,81,97,142,152,156,161,165,180],"deep":[48],"neural":[49],"network":[50],"(DNN)":[51],"technique,":[52],"we":[53],"propose":[54],"to":[55,79,112,154,193],"build":[56],"a":[57,115,120,145],"universal":[58,166,181],"for":[61,168],"all":[62,66,108],"by":[64,95],"utilizing":[65],"together.":[69],"Two":[70],"advantages":[71],"are":[72,110,127],"obtained:":[73],"1)":[74],"leveraging":[75],"more":[76],"sources":[78],"improve":[80],"accuracy,":[83],"2)":[84],"reducing":[85],"substantially":[86],"service":[87],"deployment":[88],"maintenance":[90],"costs.":[91],"We":[92],"achieve":[93],"extending":[96],"singular":[98],"value":[99],"decomposition":[100],"(SVD)":[101],"structure":[102],"of":[103,122,131],"DNNs.":[104],"The":[105],"used":[111],"first":[113],"train":[114],"single":[116],"SVD-DNN":[117],"model.":[118],"Then":[119],"series":[121],"scenario-dependent":[123,157],"linear":[124],"square":[125],"matrices":[126,158,163],"added":[128],"top":[130],"SVD":[133],"layer":[134],"updated":[136],"with":[137,160,191],"only":[138],"scenario-related":[139],"data.":[140],"At":[141],"time,":[144],"flag":[146],"indicates":[147],"different":[148],"guides":[151],"recognizer":[153],"use":[155],"together":[159],"scenario-independent":[162],"DNN":[167,182],"score":[170],"evaluation.":[171],"In":[172],"our":[173],"experiments":[174],"Microsoft":[176],"Winphone/Skype/Xbox":[177],"sets,":[179],"better":[185],"than":[186],"traditional":[187],"trained":[188],"isolated":[189],"models,":[190],"up":[192],"15.5%":[194],"relative":[195],"word":[196],"error":[197],"rate":[198],"reduction.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}