{"id":"https://openalex.org/W4289716422","doi":"https://doi.org/10.1109/taslp.2022.3196168","title":"Modeling Speech Structure to Improve T-F Masks for Speech Enhancement and Recognition","display_name":"Modeling Speech Structure to Improve T-F Masks for Speech Enhancement and Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4289716422","doi":"https://doi.org/10.1109/taslp.2022.3196168"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3196168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3196168","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/A5104084917","display_name":"Suliang Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suliang Bu","raw_affiliation_strings":["Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033518479","display_name":"Yunxin Zhao","orcid":"https://orcid.org/0000-0001-5511-3692"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunxin Zhao","raw_affiliation_strings":["Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"],"raw_orcid":"https://orcid.org/0000-0001-5511-3692","affiliations":[{"raw_affiliation_string":"Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101595500","display_name":"Tuo Zhao","orcid":"https://orcid.org/0000-0002-1536-7302"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuo Zhao","raw_affiliation_strings":["Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA"],"raw_orcid":"https://orcid.org/0000-0002-1536-7302","affiliations":[{"raw_affiliation_string":"Spoken Language and Information Processing Lab, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702012","display_name":"Shaojun Wang","orcid":"https://orcid.org/0000-0002-3680-9464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["PAII Inc., Palo Alto, USA","PAII Inc. Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAII Inc., Palo Alto, USA","institution_ids":[]},{"raw_affiliation_string":"PAII Inc. Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059125065","display_name":"Mei Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei Han","raw_affiliation_strings":["PAII Inc., Palo Alto, USA","PAII Inc. Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAII Inc., Palo Alto, USA","institution_ids":[]},{"raw_affiliation_string":"PAII Inc. Palo Alto, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9898,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7386824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"2705","last_page":"2715"},"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":0.9979000091552734,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387327551841736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.674190878868103},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6382464170455933},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5610024929046631},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.48588794469833374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4778677821159363},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4475024938583374},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42073044180870056},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.41721028089523315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3600982427597046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34745752811431885},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1477791666984558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387327551841736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.674190878868103},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6382464170455933},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5610024929046631},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.48588794469833374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4778677821159363},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4475024938583374},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42073044180870056},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.41721028089523315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3600982427597046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34745752811431885},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1477791666984558},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3196168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3196168","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/16","display_name":"Peace, Justice and strong institutions","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W190004713","https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1964538581","https://openalex.org/W1988336223","https://openalex.org/W2043216213","https://openalex.org/W2049633694","https://openalex.org/W2051170812","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2069681747","https://openalex.org/W2086139506","https://openalex.org/W2087126002","https://openalex.org/W2122994683","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2142170306","https://openalex.org/W2143027228","https://openalex.org/W2144786298","https://openalex.org/W2149425615","https://openalex.org/W2158143227","https://openalex.org/W2159531755","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2291687365","https://openalex.org/W2291877678","https://openalex.org/W2321000051","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2558539285","https://openalex.org/W2559809918","https://openalex.org/W2586584460","https://openalex.org/W2749337587","https://openalex.org/W2797110164","https://openalex.org/W2882976384","https://openalex.org/W2889343068","https://openalex.org/W2900381824","https://openalex.org/W2921144622","https://openalex.org/W2922004249","https://openalex.org/W2962866211","https://openalex.org/W2962892438","https://openalex.org/W2963041956","https://openalex.org/W2963458655","https://openalex.org/W2963941778","https://openalex.org/W2996290406","https://openalex.org/W3091570562","https://openalex.org/W3134202725","https://openalex.org/W3196559088","https://openalex.org/W4255466918","https://openalex.org/W6728770099","https://openalex.org/W6757817989","https://openalex.org/W6766224279","https://openalex.org/W6784310668","https://openalex.org/W6787533431","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Time-frequency":[0],"(TF)":[1],"masks":[2,14,128,202],"are":[3],"widely":[4],"used":[5],"in":[6,145],"speech":[7,17,61,65,69,79,120,178,196,204],"enhancement":[8],"(SE).":[9],"However,":[10],"accurately":[11],"estimating":[12],"TF":[13,60,127,148,161,171,201],"from":[15,63,108],"noisy":[16,68,109],"remains":[18],"a":[19,37,102],"challenge":[20],"to":[21,58,87,96,159,167,199],"both":[22],"statistical":[23],"or":[24,134],"neural":[25],"network":[26],"(NN)":[27],"approaches.":[28],"Statistical":[29],"model":[30,136],"based":[31],"mask":[32,132,162,172],"estimation":[33],"usually":[34],"depends":[35],"on":[36,45,177],"good":[38],"parameter":[39,137],"initialization,":[40],"while":[41],"NN-based":[42],"method":[43],"relies":[44],"setting":[46],"proper":[47],"and":[48,66,91,139,181,184,206],"stable":[49],"learning":[50],"targets.":[51,163],"To":[52],"address":[53],"these":[54],"issues,":[55],"we":[56,114,153,165],"propose":[57,166],"extract":[59],"structure":[62,198],"clean":[64,78],"partition":[67],"spectrogram":[70],"into":[71],"mutually":[72],"exclusive":[73],"regions.":[74],"We":[75],"investigate":[76],"modeling":[77,195],"by":[80,129],"utterance-specific":[81],"narrowband":[82],"complex":[83],"Gaussian":[84],"mixture":[85],"models":[86],"derive":[88],"the":[89,93,98,124,131,135,142,156,188],"regions,":[90],"using":[92,119,141,155],"region":[94,157,197],"targets":[95,158],"supervise":[97],"training":[99],"of":[100,118,147,190,194],"UNet++,":[101],"high-performance":[103],"NN,":[104],"for":[105,170,203],"predicting":[106],"regions":[107,125,144],"speech.":[110],"For":[111,150],"multichannel":[112],"SE,":[113,152],"consider":[115,154],"two":[116],"scenarios":[117],"regions:":[121],"1)":[122],"integrating":[123],"with":[126],"constraining":[130],"values":[133],"updates,":[138],"2)":[140],"predicted":[143],"place":[146],"masks.":[149],"single-channel":[151],"improve":[160,200],"Furthermore,":[164],"use":[168],"UNet++":[169],"estimation.":[173],"Our":[174],"experiment":[175],"results":[176],"recognition":[179,205],"(CHiME-3)":[180],"SE":[182],"(CHiME-3":[183],"LibriSpeech)":[185],"have":[186],"demonstrated":[187],"effectiveness":[189],"our":[191],"proposed":[192],"approach":[193],"enhancement.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}