{"id":"https://openalex.org/W2432371799","doi":"https://doi.org/10.1109/taslp.2016.2580943","title":"A Generalized Nonnegative Tensor Factorization Approach for Distant Speech Recognition With Distributed Microphones","display_name":"A Generalized Nonnegative Tensor Factorization Approach for Distant Speech Recognition With Distributed Microphones","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2432371799","doi":"https://doi.org/10.1109/taslp.2016.2580943","mag":"2432371799"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2580943","doi":"https://doi.org/10.1109/taslp.2016.2580943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2580943","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"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/A5055022808","display_name":"Seyedmahdad Mirsamadi","orcid":"https://orcid.org/0000-0002-4810-5632","observed_orcids":["https://orcid.org/0000-0002-4810-5632"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyedmahdad Mirsamadi","raw_affiliation_strings":["Center for Robust Speech Systems, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.5917,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89543082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"10","first_page":"1721","last_page":"1731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9564999938011169,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9564999938011169,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0421999990940094,"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/T11309","display_name":"Music and Audio Processing","score":0.00019999999494757503,"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/distant-speech-recognition","display_name":"distant speech recognition","score":0.8059999942779541},{"id":"https://openalex.org/keywords/far-field-speech","display_name":"far-field speech","score":0.8149999976158142},{"id":"https://openalex.org/keywords/nonnegative-tensor-factorization","display_name":"nonnegative tensor factorization","score":0.8640000224113464},{"id":"https://openalex.org/keywords/room-reverberation","display_name":"room reverberation","score":0.7900000214576721},{"id":"https://openalex.org/keywords/spectral-enhancement","display_name":"spectral enhancement","score":0.7300000190734863},{"id":"https://openalex.org/keywords/distributed-microphones","display_name":"distributed microphones","score":0.8119999766349792},{"id":"https://openalex.org/keywords/multichannel-speech-enhancement","display_name":"multichannel speech enhancement","score":0.6610000133514404},{"id":"https://openalex.org/keywords/blind-source-separation","display_name":"blind source separation","score":0.6480000019073486},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7582294344902039},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.721865177154541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7150675654411316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920331716537476},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6428138017654419},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6190019845962524},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5331952571868896},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4822574257850647},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4719003140926361},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46523135900497437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45540010929107666},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4309028089046478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35568225383758545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3491087555885315},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.29107001423835754},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2837004065513611},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.21260696649551392},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19759848713874817},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10377532243728638},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0795062780380249},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2580943","doi":"https://doi.org/10.1109/taslp.2016.2580943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2580943","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5339030464","display_name":null,"funder_award_id":"FA8750-15-1- 0205","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W14578209","https://openalex.org/W65622836","https://openalex.org/W1246381107","https://openalex.org/W1502295699","https://openalex.org/W1505878979","https://openalex.org/W1522463960","https://openalex.org/W1524333225","https://openalex.org/W1573570773","https://openalex.org/W1968493974","https://openalex.org/W1973669708","https://openalex.org/W1973787919","https://openalex.org/W1982728343","https://openalex.org/W1992475611","https://openalex.org/W2039844283","https://openalex.org/W2045405869","https://openalex.org/W2051144468","https://openalex.org/W2055070149","https://openalex.org/W2059172134","https://openalex.org/W2062164080","https://openalex.org/W2073146219","https://openalex.org/W2098434929","https://openalex.org/W2100969003","https://openalex.org/W2103088716","https://openalex.org/W2106582496","https://openalex.org/W2110606453","https://openalex.org/W2114782757","https://openalex.org/W2123832096","https://openalex.org/W2131118158","https://openalex.org/W2131968171","https://openalex.org/W2135029798","https://openalex.org/W2136682440","https://openalex.org/W2137075158","https://openalex.org/W2142352807","https://openalex.org/W2145692202","https://openalex.org/W2146871184","https://openalex.org/W2160815625","https://openalex.org/W2162514423","https://openalex.org/W2164502538","https://openalex.org/W2213952365","https://openalex.org/W2288217446","https://openalex.org/W2408656838","https://openalex.org/W2911394281","https://openalex.org/W3004970274"],"related_works":["https://openalex.org/W2408656838","https://openalex.org/W1968493974","https://openalex.org/W2902884140","https://openalex.org/W1935589317","https://openalex.org/W84068511","https://openalex.org/W2748820902","https://openalex.org/W2955605595","https://openalex.org/W2591355762","https://openalex.org/W1993411870","https://openalex.org/W1973669708"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,55],"recognition":[2],"(ASR)":[3],"using":[4,36,159],"distant":[5,151],"(far-field)":[6],"microphones":[7,111],"is":[8,16,74,89,113,133,142],"a":[9,28,58,148],"challenging":[10],"task,":[11],"in":[12,49,94,135,138,176],"which":[13,81,132,139],"room":[14],"reverberation":[15],"one":[17],"of":[18,22,45,60,71,115,169],"the":[19,43,53,65,77,86,104],"primary":[20],"causes":[21],"performance":[23],"degradation.":[24],"This":[25],"study":[26],"proposes":[27],"multichannel":[29],"spectral":[30],"enhancement":[31],"method":[32,41,106],"for":[33,76,85],"reverberation-robust":[34],"ASR":[35,152],"distributed":[37],"microphones.":[38],"The":[39,68,120],"proposed":[40,105],"uses":[42],"techniques":[44],"nonnegative":[46],"tensor":[47,78],"factorization":[48],"order":[50],"to":[51,91,125],"identify":[52],"clean":[54],"component":[56],"from":[57,64],"set":[59],"observed":[61],"reverberant":[62,96],"spectrograms":[63],"different":[66,130],"channels.":[67],"general":[69],"family":[70],"alpha-beta":[72],"divergences":[73],"used":[75],"decomposition":[79],"task":[80,153],"provides":[82],"increased":[83],"flexibility":[84],"algorithm":[87,121],"and":[88,112,117,158,172,179],"shown":[90],"provide":[92],"improvements":[93,168],"highly":[95],"scenarios.":[97,181],"Unlike":[98],"many":[99],"conventional":[100],"array":[101],"processing":[102],"solutions,":[103],"does":[107],"not":[108],"require":[109],"closely-spaced":[110],"independent":[114],"source":[116],"microphone":[118],"locations.":[119],"can":[122],"automatically":[123],"adapt":[124],"unbalanced":[126],"direct-to-reverberation":[127],"ratios":[128],"among":[129],"channels,":[131],"useful":[134],"blind":[136],"scenarios":[137],"no":[140],"information":[141],"available":[143],"about":[144],"source-to-microphone":[145],"distances.":[146],"For":[147],"medium":[149],"vocabulary":[150],"based":[154],"on":[155],"TIMIT":[156],"utterances,":[157],"clean-trained":[160],"deep":[161],"neural":[162],"network":[163],"acoustic":[164],"models,":[165],"absolute":[166],"WER":[167],"+17.2%,":[170],"+20.7%,":[171],"+23.2%":[173],"are":[174],"achieved":[175],"single-channel,":[177],"two-channel,":[178],"four-channel":[180]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}