{"id":"https://openalex.org/W3032514799","doi":"https://doi.org/10.1109/taslp.2020.2998279","title":"Complex Spectral Mapping for Single- and Multi-Channel Speech Enhancement and Robust ASR","display_name":"Complex Spectral Mapping for Single- and Multi-Channel Speech Enhancement and Robust ASR","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3032514799","doi":"https://doi.org/10.1109/taslp.2020.2998279","mag":"3032514799","pmid":"https://pubmed.ncbi.nlm.nih.gov/33748326"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2998279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2998279","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, 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 Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277 USA","Department of Computer Science and Engineering & the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering & the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":17.8811,"has_fulltext":false,"cited_by_count":216,"citation_normalized_percentile":{"value":0.9962818,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"1778","last_page":"1787"},"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":0.9987999796867371,"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":0.9972000122070312,"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/microphone-array","display_name":"Microphone array","score":0.6858586072921753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6596379280090332},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6543880105018616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6332204341888428},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5740200877189636},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.539391040802002},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.48764264583587646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46569952368736267},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43708446621894836},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4113946557044983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39013180136680603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711395263671875},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1551145613193512},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.1479826271533966},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12018623948097229}],"concepts":[{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6858586072921753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596379280090332},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6543880105018616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6332204341888428},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5740200877189636},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.539391040802002},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.48764264583587646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46569952368736267},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43708446621894836},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4113946557044983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39013180136680603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711395263671875},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1551145613193512},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.1479826271533966},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12018623948097229},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.2998279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2998279","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"},{"id":"pmid:33748326","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33748326","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7971156","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971156","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7971156","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971156","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W330298975","https://openalex.org/W1482149378","https://openalex.org/W1544785557","https://openalex.org/W1555217905","https://openalex.org/W1901129140","https://openalex.org/W1982172017","https://openalex.org/W1992879732","https://openalex.org/W2095072097","https://openalex.org/W2120847449","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2291877678","https://openalex.org/W2400339399","https://openalex.org/W2509456128","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2568308529","https://openalex.org/W2599685671","https://openalex.org/W2641129314","https://openalex.org/W2714487941","https://openalex.org/W2718052359","https://openalex.org/W2774389566","https://openalex.org/W2792764867","https://openalex.org/W2803322398","https://openalex.org/W2889698889","https://openalex.org/W2891219041","https://openalex.org/W2891984996","https://openalex.org/W2892163332","https://openalex.org/W2897977894","https://openalex.org/W2900010751","https://openalex.org/W2900893004","https://openalex.org/W2902894493","https://openalex.org/W2922439870","https://openalex.org/W2923728956","https://openalex.org/W2938386503","https://openalex.org/W2962866211","https://openalex.org/W2962892438","https://openalex.org/W2963189033","https://openalex.org/W2963317762","https://openalex.org/W2963446712","https://openalex.org/W2963751183","https://openalex.org/W2966212213","https://openalex.org/W2972460025","https://openalex.org/W2982471419","https://openalex.org/W2991361823","https://openalex.org/W3121132363","https://openalex.org/W4211261061","https://openalex.org/W6639824700","https://openalex.org/W6749825310","https://openalex.org/W6766475400"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188"],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,60,104],"complex":[4,49,54,94,99],"spectral":[5,50,95],"mapping":[6],"approach":[7],"for":[8,92],"single-":[9],"and":[10,25,35,118,132,143,157],"multi-channel":[11,93],"speech":[12,116],"enhancement,":[13],"where":[14],"deep":[15],"neural":[16],"networks":[17],"(DNNs)":[18],"are":[19,56,77],"used":[20,57],"to":[21,58,87],"predict":[22],"the":[23,30,81,85,89,115,122,140,150],"real":[24],"imaginary":[26],"(RI)":[27],"components":[28,69,83],"of":[29,70,84,107,121,146,154],"direct-path":[31],"signal":[32],"from":[33],"noisy":[34],"reverberant":[36],"ones.":[37],"The":[38,44,52,67],"proposed":[39],"system":[40,128],"contains":[41],"two":[42],"DNNs.":[43],"first":[45],"one":[46],"performs":[47],"single-channel":[48],"mapping.":[51,96],"estimated":[53,98],"spectra":[55],"compute":[59],"minimum":[61],"variance":[62],"distortion-less":[63],"response":[64],"(MVDR)":[65],"beamformer.":[66],"RI":[68,82],"beamforming":[71],"results,":[72],"which":[73],"encode":[74],"spatial":[75],"information,":[76],"then":[78],"combined":[79],"with":[80],"mixture":[86],"train":[88],"second":[90],"DNN":[91],"With":[97],"spectra,":[100],"we":[101],"also":[102],"propose":[103],"novel":[105],"method":[106],"time-varying":[108],"beamforming.":[109],"State-of-the-art":[110],"performance":[111],"is":[112],"obtained":[113],"on":[114,139],"enhancement":[117],"recognition":[119],"tasks":[120,145],"CHiME-4":[123],"corpus.":[124],"More":[125],"specifically,":[126],"our":[127],"obtains":[129],"6.82%,":[130],"3.19%":[131],"2.00%":[133],"word":[134],"error":[135],"rates":[136],"(WER)":[137],"respectively":[138],"single-,":[141],"two-,":[142],"six-microphone":[144],"CHiME-4,":[147],"significantly":[148],"surpassing":[149],"current":[151],"best":[152],"results":[153],"9.15%,":[155],"3.91%":[156],"2.24%":[158],"WER.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":46},{"year":2022,"cited_by_count":39},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}