{"id":"https://openalex.org/W2291652038","doi":"https://doi.org/10.1109/asru.2015.7404836","title":"Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition","display_name":"Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2291652038","doi":"https://doi.org/10.1109/asru.2015.7404836","mag":"2291652038"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089667871","display_name":"Deblin Bagchi","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deblin Bagchi","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I. Mandel","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongqiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042983246","display_name":"Andrew Plummer","orcid":"https://orcid.org/0000-0003-0082-3480"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Plummer","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"496","last_page":"503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9994000196456909,"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/source-separation","display_name":"Source separation","score":0.7739326357841492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.760573148727417},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.7135659456253052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6873584985733032},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6585330963134766},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.626774251461029},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.601585328578949},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5923198461532593},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5236984491348267},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5069515705108643},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5049894452095032},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4287794232368469},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.420045405626297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40984854102134705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35910338163375854},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.28196001052856445},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16682860255241394},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11740747094154358}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7739326357841492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760573148727417},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7135659456253052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6873584985733032},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6585330963134766},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.626774251461029},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.601585328578949},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5923198461532593},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5236984491348267},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5069515705108643},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5049894452095032},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4287794232368469},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.420045405626297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40984854102134705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35910338163375854},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28196001052856445},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16682860255241394},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11740747094154358},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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":[{"id":"doi:10.1109/asru.2015.7404836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W14899464","https://openalex.org/W58750608","https://openalex.org/W160800111","https://openalex.org/W1524333225","https://openalex.org/W1571203213","https://openalex.org/W1967590528","https://openalex.org/W1973681148","https://openalex.org/W1989364685","https://openalex.org/W1991904167","https://openalex.org/W1997418877","https://openalex.org/W2006129368","https://openalex.org/W2017608047","https://openalex.org/W2035576074","https://openalex.org/W2041638389","https://openalex.org/W2042071805","https://openalex.org/W2042141988","https://openalex.org/W2044893557","https://openalex.org/W2057826000","https://openalex.org/W2062164080","https://openalex.org/W2063224314","https://openalex.org/W2079362249","https://openalex.org/W2101045344","https://openalex.org/W2111890897","https://openalex.org/W2114719288","https://openalex.org/W2129171989","https://openalex.org/W2137075158","https://openalex.org/W2148613904","https://openalex.org/W2152919025","https://openalex.org/W2198021053","https://openalex.org/W2289394825","https://openalex.org/W2290318471","https://openalex.org/W2296581541","https://openalex.org/W2397728357","https://openalex.org/W2399557756","https://openalex.org/W2404568753","https://openalex.org/W2408713104","https://openalex.org/W2489311264","https://openalex.org/W4253158045","https://openalex.org/W6631362777","https://openalex.org/W6643899157","https://openalex.org/W6651792446","https://openalex.org/W6662018355","https://openalex.org/W6664675605","https://openalex.org/W6676895149","https://openalex.org/W6682650297","https://openalex.org/W6697251715","https://openalex.org/W6712476441","https://openalex.org/W6712706723","https://openalex.org/W6713570806","https://openalex.org/W6713729801"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2380771148","https://openalex.org/W2539388437","https://openalex.org/W2107688514"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"systems":[3,38],"suffer":[4],"from":[5,136],"severe":[6],"performance":[7,191],"degradation":[8],"in":[9,59,73,142],"the":[10,47,54,84,95,102,146,149,156,161,180,185,190],"presence":[11],"of":[12,40,56,70,86,97,148,163,171],"myriad":[13],"complicating":[14],"factors":[15],"such":[16],"as":[17],"noise,":[18],"reverberation,":[19],"multiple":[20,23,140],"speech":[21,58],"sources,":[22],"recording":[24],"devices,":[25],"etc.":[26],"Previous":[27],"challenges":[28],"have":[29],"sparked":[30],"much":[31],"innovation":[32],"when":[33],"it":[34],"comes":[35],"to":[36,67,78,94,139,144],"designing":[37],"capable":[39],"handling":[41],"these":[42,80],"complications.":[43],"In":[44,76],"this":[45],"spirit,":[46],"CHiME-3":[48],"challenge":[49],"presents":[50],"system":[51,173],"builders":[52],"with":[53],"task":[55],"recognizing":[57],"a":[60,74,89,98,111,164],"real-world":[61],"noisy":[62],"setting":[63],"wherein":[64],"speakers":[65],"talk":[66],"an":[68],"array":[69],"6":[71],"microphones":[72],"tablet.":[75],"order":[77,143],"address":[79],"issues,":[81],"we":[82],"explore":[83],"effectiveness":[85],"first":[87],"applying":[88],"model-based":[90],"source":[91,103,123],"separation":[92,124],"mask":[93],"output":[96],"beamformer":[99,187],"that":[100,117,176],"combines":[101],"signals":[104],"recorded":[105],"by":[106,110,160],"each":[107],"microphone,":[108],"followed":[109],"DNN-based":[112],"front":[113],"end":[114],"spectral":[115,181],"mapper":[116,182],"predicts":[118],"clean":[119],"filterbank":[120],"features.":[121],"The":[122],"algorithm":[125,167,188],"MESSL":[126,178],"(Model-based":[127],"EM":[128],"Source":[129],"Separation":[130],"and":[131,179],"Localization)":[132],"has":[133],"been":[134],"extended":[135],"two":[137,157],"channels":[138,141],"meet":[145],"demands":[147],"challenge.":[150],"We":[151],"report":[152],"on":[153,184],"interactions":[154],"between":[155],"systems,":[158],"cross-cut":[159],"use":[162],"robust":[165],"beamforming":[166],"called":[168],"BeamformIt.":[169],"Evaluations":[170],"different":[172],"settings":[174],"reveal":[175],"combining":[177],"together":[183],"baseline":[186],"boosts":[189],"substantially.":[192]},"counts_by_year":[{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}