{"id":"https://openalex.org/W2035576074","doi":"https://doi.org/10.1109/taslp.2014.2305833","title":"Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition","display_name":"Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition","publication_year":2014,"publication_date":"2014-02-12","ids":{"openalex":"https://openalex.org/W2035576074","doi":"https://doi.org/10.1109/taslp.2014.2305833","mag":"2035576074"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2305833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2305833","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,"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"},"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/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"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":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"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":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering and Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#"],"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 and Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":15.3093,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99384159,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"22","issue":"4","first_page":"826","last_page":"835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9993000030517578,"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/speech-recognition","display_name":"Speech recognition","score":0.7511535882949829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6853671073913574},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.572365403175354},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.515270471572876},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5094760060310364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5055437088012695},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5038895010948181},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4773454964160919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4679281711578369},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4475187659263611},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.441129595041275},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4256371855735779},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.423764705657959},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15048274397850037}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7511535882949829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6853671073913574},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.572365403175354},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.515270471572876},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5094760060310364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5055437088012695},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5038895010948181},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4773454964160919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4679281711578369},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4475187659263611},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.441129595041275},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4256371855735779},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.423764705657959},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15048274397850037},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2014.2305833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2305833","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,"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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W71792008","https://openalex.org/W88081813","https://openalex.org/W160800111","https://openalex.org/W1665214252","https://openalex.org/W1904365287","https://openalex.org/W1950777589","https://openalex.org/W1963970749","https://openalex.org/W1964118201","https://openalex.org/W1967590528","https://openalex.org/W1976637928","https://openalex.org/W1981817333","https://openalex.org/W1981936647","https://openalex.org/W1988541906","https://openalex.org/W1989364685","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2012204351","https://openalex.org/W2027701650","https://openalex.org/W2034040413","https://openalex.org/W2052667477","https://openalex.org/W2062164080","https://openalex.org/W2062227835","https://openalex.org/W2066755975","https://openalex.org/W2066850331","https://openalex.org/W2085191029","https://openalex.org/W2086139506","https://openalex.org/W2113651538","https://openalex.org/W2136922672","https://openalex.org/W2137075158","https://openalex.org/W2141411743","https://openalex.org/W2145475542","https://openalex.org/W2146083413","https://openalex.org/W2146423524","https://openalex.org/W2146502635","https://openalex.org/W2147768505","https://openalex.org/W2150866759","https://openalex.org/W2160306971","https://openalex.org/W2163605009","https://openalex.org/W2168379380","https://openalex.org/W2213952365","https://openalex.org/W2290318471","https://openalex.org/W2294059674","https://openalex.org/W2394967684","https://openalex.org/W2748434850","https://openalex.org/W2914878751","https://openalex.org/W2964138484","https://openalex.org/W6637242042","https://openalex.org/W6640036494","https://openalex.org/W6677106874","https://openalex.org/W6681435938","https://openalex.org/W6684191040","https://openalex.org/W6688428952","https://openalex.org/W6696761078","https://openalex.org/W6711908631"],"related_works":["https://openalex.org/W3081694532","https://openalex.org/W1969211203","https://openalex.org/W1517958729","https://openalex.org/W2092272653","https://openalex.org/W4387002515","https://openalex.org/W1992704972","https://openalex.org/W1980045272","https://openalex.org/W4226126880","https://openalex.org/W2400338474","https://openalex.org/W159361053"],"abstract_inverted_index":{"Recently,":[0],"supervised":[1],"classification":[2],"has":[3],"been":[4],"shown":[5],"to":[6,74,147],"work":[7],"well":[8],"for":[9,26,116],"the":[10,56,60,70,81,89,137,156,164,170,193,196],"task":[11],"of":[12,20,37],"speech":[13,29,172],"separation.":[14],"We":[15,97],"perform":[16],"an":[17],"in-depth":[18],"evaluation":[19],"such":[21],"techniques":[22],"as":[23],"a":[24,63,100,113],"front-end":[25,35,83,174],"noise-robust":[27],"automatic":[28],"recognition":[30],"(ASR).":[31],"The":[32,40,49],"proposed":[33,82,171],"separation":[34,173],"consists":[36],"two":[38],"stages.":[39],"first":[41,61],"stage":[42,51],"removes":[43],"additive":[44],"noise":[45],"via":[46],"time-frequency":[47],"masking.":[48],"second":[50],"addresses":[52],"channel":[53,162],"mismatch":[54],"and":[55,123],"distortions":[57],"introduced":[58],"by":[59,185],"stage;":[62],"non-linear":[64],"function":[65],"is":[66,145,175],"learned":[67],"that":[68,80,108,127],"maps":[69],"masked":[71],"spectral":[72,153],"features":[73,154,183],"their":[75],"clean":[76,95],"counterpart.":[77],"Results":[78,125],"show":[79,126],"substantially":[84],"improves":[85,130],"ASR":[86,117],"performance":[87,131],"when":[88,143,169],"acoustic":[90],"models":[91,148],"are":[92,141,167,191],"trained":[93,149],"in":[94,132],"conditions.":[96,135],"also":[98],"propose":[99],"diagonal":[101],"feature":[102],"discriminant":[103],"linear":[104],"regression":[105],"(dFDLR)":[106],"adaptation":[107],"can":[109],"be":[110],"performed":[111],"on":[112,195],"per-utterance":[114],"basis":[115],"systems":[118],"employing":[119],"deep":[120],"neural":[121],"networks":[122],"HMM.":[124],"dFDLR":[128,144,186],"consistently":[129],"all":[133],"test":[134],"Surprisingly,":[136],"best":[138,165,194],"average":[139],"results":[140,166,190],"obtained":[142,168],"applied":[146],"using":[150,181],"noisy":[151],"log-Mel":[152,182],"from":[155],"multi-condition":[157,179],"training":[158,180],"set.":[159],"With":[160],"no":[161],"mismatch,":[163],"used":[176],"along":[177],"with":[178],"followed":[184],"adaptation.":[187],"Both":[188],"these":[189],"among":[192],"Aurora-4":[197],"dataset.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}