{"id":"https://openalex.org/W3162493033","doi":"https://doi.org/10.1109/taslp.2021.3079813","title":"Two Heads are Better Than One: A Two-Stage Complex Spectral Mapping Approach for Monaural Speech Enhancement","display_name":"Two Heads are Better Than One: A Two-Stage Complex Spectral Mapping Approach for Monaural Speech Enhancement","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3162493033","doi":"https://doi.org/10.1109/taslp.2021.3079813","mag":"3162493033"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3079813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3079813","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/A5053757616","display_name":"Andong Li","orcid":"https://orcid.org/0000-0003-4094-8448"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Andong Li","raw_affiliation_strings":["Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679522","display_name":"Wenzhe Liu","orcid":"https://orcid.org/0000-0002-0827-6883"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Liu","raw_affiliation_strings":["Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070266277","display_name":"Chengshi Zheng","orcid":"https://orcid.org/0000-0001-5656-994X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":["Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, China"],"affiliations":[{"raw_affiliation_string":"Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100711527","display_name":"Xiaodong Li","orcid":"https://orcid.org/0000-0002-4170-0076"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Li","raw_affiliation_strings":["Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053757616"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":20.8323,"has_fulltext":false,"cited_by_count":190,"citation_normalized_percentile":{"value":0.99779161,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"1829","last_page":"1843"},"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":0.9958999752998352,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.9154117703437805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8227936029434204},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6708847880363464},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6571062207221985},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6400579810142517},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.521632969379425},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5194455981254578},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4977617561817169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3779580891132355},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3405095934867859},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2078741192817688}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9154117703437805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227936029434204},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6708847880363464},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6571062207221985},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6400579810142517},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.521632969379425},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5194455981254578},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4977617561817169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3779580891132355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3405095934867859},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2078741192817688},{"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3079813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3079813","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":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":108,"referenced_works":["https://openalex.org/W165956390","https://openalex.org/W190004713","https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1523680888","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1974387177","https://openalex.org/W1978808268","https://openalex.org/W2024490156","https://openalex.org/W2034040413","https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2069710780","https://openalex.org/W2070126272","https://openalex.org/W2120847449","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2156387975","https://openalex.org/W2194775991","https://openalex.org/W2267126114","https://openalex.org/W2291877678","https://openalex.org/W2296073425","https://openalex.org/W2364134690","https://openalex.org/W2502312327","https://openalex.org/W2516001803","https://openalex.org/W2516547830","https://openalex.org/W2550397165","https://openalex.org/W2567070169","https://openalex.org/W2603567530","https://openalex.org/W2802304149","https://openalex.org/W2889442120","https://openalex.org/W2897371647","https://openalex.org/W2899771611","https://openalex.org/W2905649134","https://openalex.org/W2906042495","https://openalex.org/W2943554574","https://openalex.org/W2943895317","https://openalex.org/W2949756029","https://openalex.org/W2952218014","https://openalex.org/W2953318193","https://openalex.org/W2962866211","https://openalex.org/W2963103134","https://openalex.org/W2963189033","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963452667","https://openalex.org/W2963840672","https://openalex.org/W2963970792","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2972948005","https://openalex.org/W2981436548","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W2998657200","https://openalex.org/W3002439978","https://openalex.org/W3010851250","https://openalex.org/W3015526955","https://openalex.org/W3016361963","https://openalex.org/W3016447038","https://openalex.org/W3027637851","https://openalex.org/W3032514799","https://openalex.org/W3034763882","https://openalex.org/W3042857426","https://openalex.org/W3094040572","https://openalex.org/W3094607766","https://openalex.org/W3094910704","https://openalex.org/W3095057960","https://openalex.org/W3096008106","https://openalex.org/W3096408984","https://openalex.org/W3096831638","https://openalex.org/W3097034112","https://openalex.org/W3097681199","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3101133222","https://openalex.org/W3103434036","https://openalex.org/W3133046651","https://openalex.org/W3134695619","https://openalex.org/W3147539069","https://openalex.org/W3161140524","https://openalex.org/W4210849719","https://openalex.org/W4253928870","https://openalex.org/W4300983915","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6682889407","https://openalex.org/W6696085341","https://openalex.org/W6724804524","https://openalex.org/W6731370813","https://openalex.org/W6739901393","https://openalex.org/W6751512325","https://openalex.org/W6756040250","https://openalex.org/W6757632829","https://openalex.org/W6757668070","https://openalex.org/W6770282137","https://openalex.org/W6772622344","https://openalex.org/W6777701575","https://openalex.org/W6781755050","https://openalex.org/W6784310668","https://openalex.org/W6784484293","https://openalex.org/W6784661014","https://openalex.org/W6790255001"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W1974981856","https://openalex.org/W1983045063","https://openalex.org/W2045506488","https://openalex.org/W4321794819","https://openalex.org/W1657880117","https://openalex.org/W2538939196","https://openalex.org/W3045520545"],"abstract_inverted_index":{"For":[0],"challenging":[1],"acoustic":[2],"scenarios":[3],"as":[4,112],"low":[5],"signal-to-noise":[6],"ratios,":[7],"current":[8],"speech":[9,21,46],"enhancement":[10,47],"systems":[11,212],"usually":[12],"suffer":[13],"from":[14,22],"performance":[15,174,208],"bottleneck":[16],"in":[17,48,77,104,136,229],"extracting":[18],"the":[19,23,49,58,66,78,89,101,105,113,123,137,142,148,153,166,176,223],"target":[20],"mixtures":[24],"within":[25],"one":[26],"step.":[27],"To":[28,99,146],"address":[29],"this":[30],"issue,":[31],"we":[32,156],"propose":[33,157],"a":[34,41,94,158],"novel":[35],"complex":[36,96],"spectral":[37],"mapping":[38],"approach":[39,205],"with":[40,88],"two-stage":[42],"pipeline":[43],"for":[44],"monaural":[45],"time-frequency":[50],"domain.":[51],"The":[52,129],"proposed":[53,204,227],"algorithm":[54],"aims":[55],"to":[56,92,140],"decouple":[57],"primal":[59],"problem":[60],"into":[61],"multiple":[62],"sub-problems,":[63],"which":[64,85,163],"follows":[65],"classic":[67],"proverb,":[68],"\u201ctwo":[69],"heads":[70],"are":[71],"better":[72,172],"than":[73],"one\u201d.":[74],"More":[75],"specifically,":[76],"first":[79],"stage,":[80,107],"only":[81],"magnitude":[82],"is":[83,86,119,126,134],"estimated,":[84],"incorporated":[87],"noisy":[90],"phase":[91,124],"obtain":[93],"coarse":[95],"spectrum":[97],"estimation.":[98],"facilitate":[100],"previous":[102,210],"estimation,":[103],"second":[106,138],"an":[108],"auxiliary":[109],"network":[110],"serves":[111],"post-processing":[114],"module,":[115,162],"where":[116],"residual":[117,131],"noise":[118],"further":[120,221],"suppressed":[121],"and":[122,169,192],"information":[125],"effectively":[127],"modified.":[128],"global":[130],"connection":[132],"strategy":[133],"adopted":[135],"stage":[139],"accelerate":[141],"training":[143],"convergence":[144],"speed.":[145],"alleviate":[147],"parameter":[149],"burden":[150],"caused":[151],"by":[152],"multi-stage":[154],"pipeline,":[155],"light-weight":[159],"temporal":[160],"convolutional":[161],"substantially":[164],"decreases":[165],"trainable":[167],"parameters":[168],"obtains":[170],"even":[171],"objective":[173],"over":[175,209],"original":[177],"version.":[178],"We":[179],"conduct":[180],"extensive":[181],"experiments":[182],"on":[183],"three":[184],"standard":[185],"corpora,":[186],"including":[187],"WSJ0-SI84,":[188],"DNS":[189],"Challenge":[190],"dataset,":[191],"Voice":[193],"Bank":[194],"+":[195],"DEMAND":[196],"dataset.":[197],"Objective":[198],"test":[199,219],"results":[200,220],"demonstrate":[201],"that":[202],"our":[203,226],"achieves":[206],"state-of-the-art":[207],"advanced":[211],"under":[213],"various":[214],"conditions.":[215],"Meanwhile,":[216],"subjective":[217,232],"listening":[218],"validate":[222],"superiority":[224],"of":[225,231],"method":[228],"terms":[230],"quality.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":52},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":9}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}