{"id":"https://openalex.org/W2801798988","doi":"https://doi.org/10.1109/icassp.2018.8461939","title":"Sequence Modeling in Unsupervised Single-Channel Overlapped Speech Recognition","display_name":"Sequence Modeling in Unsupervised Single-Channel Overlapped Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2801798988","doi":"https://doi.org/10.1109/icassp.2018.8461939","mag":"2801798988"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"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":true,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"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":"Jasha Droppo","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002433660"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.2577,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93591482,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"abs 1704 1985","issue":null,"first_page":"4809","last_page":"4813"},"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":0.9990000128746033,"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/discriminative-model","display_name":"Discriminative model","score":0.7664504051208496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7658757567405701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7191247940063477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261430740356445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5044101476669312},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4999244213104248},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4915517270565033},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4488256573677063},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43485546112060547},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43442755937576294},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4225085973739624},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33429694175720215}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7664504051208496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658757567405701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7191247940063477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261430740356445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5044101476669312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4999244213104248},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4915517270565033},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4488256573677063},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43485546112060547},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43442755937576294},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4225085973739624},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33429694175720215},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/10","display_name":"Reduced inequalities","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1748744376","https://openalex.org/W1964538581","https://openalex.org/W1991139021","https://openalex.org/W2060822897","https://openalex.org/W2087368178","https://openalex.org/W2122028591","https://openalex.org/W2127141656","https://openalex.org/W2144763279","https://openalex.org/W2221409856","https://openalex.org/W2296073425","https://openalex.org/W2315268655","https://openalex.org/W2327501763","https://openalex.org/W2513383847","https://openalex.org/W2533523411","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2627092829","https://openalex.org/W2698117193","https://openalex.org/W2746192915","https://openalex.org/W2890505457","https://openalex.org/W2892025684","https://openalex.org/W2962961016","https://openalex.org/W2963773971","https://openalex.org/W3099832538","https://openalex.org/W6702097088","https://openalex.org/W6736173540","https://openalex.org/W6749240465","https://openalex.org/W6754547940","https://openalex.org/W6754686218","https://openalex.org/W6785623113"],"related_works":["https://openalex.org/W2395910192","https://openalex.org/W2112752961","https://openalex.org/W2113687551","https://openalex.org/W107086600","https://openalex.org/W2126322296","https://openalex.org/W4205820553","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2251441308","https://openalex.org/W2916997151"],"abstract_inverted_index":{"Unsupervised":[0],"single-channel":[1],"overlapped":[2,152],"speech":[3,13,31,112],"recognition":[4,14],"is":[5,64,114,120],"one":[6],"of":[7,77,93,133,147],"the":[8,38,46,57,71,75,78,86,90,94,110,117,150],"hardest":[9],"problems":[10,17],"in":[11,109,149],"automatic":[12],"(ASR).":[15],"The":[16,123],"can":[18,126],"be":[19,127],"modularized":[20],"into":[21,89],"three":[22],"sub-problems:":[23],"frame-wise":[24],"interpreting,":[25],"sequence":[26,73,136],"level":[27,102],"speaker":[28],"tracing":[29],"and":[30,74,135,154],"recognition.":[32],"Nevertheless,":[33],"previous":[34],"acoustic":[35],"models":[36,55,67],"formulate":[37],"correlation":[39,60],"between":[40],"sequential":[41,58],"labels":[42],"implicitly,":[43],"which":[44,139],"limit":[45],"modeling":[47],"effect.":[48],"In":[49],"this":[50],"work,":[51],"we":[52,82],"include":[53],"explicit":[54],"for":[56],"label":[59],"during":[61],"training.":[62],"This":[63],"relevant":[65],"to":[66,84],"given":[68],"by":[69],"both":[70],"feature":[72],"output":[76],"last":[79],"frame.":[80],"Moreover,":[81],"propose":[83],"integrate":[85],"linguistic":[87],"information":[88],"assignment":[91],"decision":[92],"permutation":[95],"invariant":[96],"training":[97],"(PIT).":[98],"Namely,":[99],"a":[100],"senone":[101],"neural":[103],"network":[104],"language":[105],"model":[106],"(NNLM)":[107],"trained":[108],"clean":[111],"alignment":[113],"integrated,":[115],"while":[116],"objective":[118],"function":[119],"still":[121],"cross-entropy.":[122],"proposed":[124],"methods":[125],"combined":[128],"with":[129],"an":[130],"improved":[131],"version":[132],"PIT":[134],"discriminative":[137],"training,":[138],"brings":[140],"about":[141],"further":[142],"over":[143],"10%":[144],"relative":[145],"improvement":[146],"WER":[148],"artificial":[151],"Switchboard":[153],"hub5e-swb":[155],"dataset.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}