{"id":"https://openalex.org/W2598036111","doi":"https://doi.org/10.1109/taslp.2017.2687829","title":"Features for Masking-Based Monaural Speech Separation in Reverberant Conditions","display_name":"Features for Masking-Based Monaural Speech Separation in Reverberant Conditions","publication_year":2017,"publication_date":"2017-03-27","ids":{"openalex":"https://openalex.org/W2598036111","doi":"https://doi.org/10.1109/taslp.2017.2687829","mag":"2598036111"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2687829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2687829","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/A5012541772","display_name":"Masood Delfarah","orcid":"https://orcid.org/0000-0002-8354-0832"},"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":"Masood Delfarah","raw_affiliation_strings":["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"]}]},{"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"],"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":8.2205,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98198771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"25","issue":"5","first_page":"1085","last_page":"1094"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8320064544677734},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7795217037200928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7482820749282837},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6874816417694092},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.48733529448509216},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4808662533760071},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4780307710170746},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.4138130247592926},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4120978116989136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3885011374950409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3817949891090393},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25281524658203125},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21455255150794983}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8320064544677734},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7795217037200928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7482820749282837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6874816417694092},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.48733529448509216},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4808662533760071},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4780307710170746},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.4138130247592926},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4120978116989136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3885011374950409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817949891090393},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25281524658203125},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21455255150794983},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2687829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2687829","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":[],"awards":[{"id":"https://openalex.org/G8822322065","display_name":null,"funder_award_id":"FA9550-12-1-0130","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W67398352","https://openalex.org/W118588063","https://openalex.org/W1493299544","https://openalex.org/W1495679096","https://openalex.org/W1515932869","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1635512741","https://openalex.org/W1665214252","https://openalex.org/W1790748249","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1983108229","https://openalex.org/W1989364685","https://openalex.org/W1990449877","https://openalex.org/W1990934990","https://openalex.org/W2006129368","https://openalex.org/W2010275911","https://openalex.org/W2017608047","https://openalex.org/W2020438552","https://openalex.org/W2044893557","https://openalex.org/W2057200980","https://openalex.org/W2063669828","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2090861223","https://openalex.org/W2095705004","https://openalex.org/W2096496615","https://openalex.org/W2104862701","https://openalex.org/W2114218864","https://openalex.org/W2115129089","https://openalex.org/W2117678320","https://openalex.org/W2137075158","https://openalex.org/W2138019504","https://openalex.org/W2141998673","https://openalex.org/W2153119843","https://openalex.org/W2164432048","https://openalex.org/W2167314872","https://openalex.org/W2168379380","https://openalex.org/W2304609584","https://openalex.org/W2326699523","https://openalex.org/W2344535577","https://openalex.org/W2398826216","https://openalex.org/W2404892923","https://openalex.org/W2509674098","https://openalex.org/W2964121744","https://openalex.org/W3124794156","https://openalex.org/W4233392025","https://openalex.org/W4249052411","https://openalex.org/W4253928870","https://openalex.org/W4255949318","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6674330103","https://openalex.org/W6712560600"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2732511158","https://openalex.org/W2621851636","https://openalex.org/W2538939196","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,8,84,96],"separation":[2,77],"is":[3,44,79,89,112],"a":[4,18,99,134],"fundamental":[5],"problem":[6,13],"in":[7,64,92,98,153,160],"and":[9,46,76,95,105,140],"signal":[10],"processing.":[11],"This":[12],"can":[14,47],"be":[15],"approached":[16],"from":[17,28,49,158],"supervised":[19],"learning":[20,74],"perspective":[21],"by":[22,114],"predicting":[23],"an":[24,57],"ideal":[25],"time-frequency":[26],"mask":[27,42],"features":[29,62,142],"of":[30,60,101,123],"noisy":[31],"speech.":[32],"In":[33,52,126],"reverberant":[34,161],"conditions":[35,155],"at":[36],"low":[37],"signal-to-noise":[38],"ratios":[39],"(SNRs),":[40],"accurate":[41],"prediction":[43],"challenging":[45],"benefit":[48],"effective":[50],"features.":[51],"this":[53],"paper,":[54],"we":[55,128],"investigate":[56],"extensive":[58],"set":[59],"acoustic-phonetic":[61],"extracted":[63],"adverse":[65],"conditions.":[66,162],"Deep":[67],"neural":[68],"networks":[69],"are":[70,156],"used":[71],"as":[72],"the":[73],"machine,":[75],"performance":[78,88,110],"evaluated":[80,91],"using":[81,115,133],"standard":[82],"objective":[83],"intelligibility":[85],"metrics.":[86],"Separation":[87],"systematically":[90],"both":[93],"nonspeech":[94],"interference,":[97],"variety":[100],"SNRs,":[102],"reverberation":[103],"times,":[104],"direct-to-reverberant":[106],"energy":[107],"ratios.":[108],"Considerable":[109],"improvement":[111],"observed":[113],"contextual":[116],"information,":[117],"likely":[118],"due":[119],"to":[120],"temporal":[121],"effects":[122],"room":[124],"reverberation.":[125],"addition,":[127],"construct":[129],"feature":[130,151],"combination":[131],"sets":[132,152],"sequential":[135],"floating":[136],"forward":[137],"selection":[138],"algorithm,":[139],"combined":[141],"outperform":[143],"individual":[144],"ones.":[145],"We":[146],"also":[147],"find":[148],"that":[149],"optimal":[150],"anechoic":[154],"different":[157],"those":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}