{"id":"https://openalex.org/W4379984888","doi":"https://doi.org/10.1109/taslp.2023.3284522","title":"Harmonic Attention for Monaural Speech Enhancement","display_name":"Harmonic Attention for Monaural Speech Enhancement","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4379984888","doi":"https://doi.org/10.1109/taslp.2023.3284522"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3284522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284522","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/A5106558173","display_name":"Tianrui Wang","orcid":"https://orcid.org/0000-0002-2765-5889"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["Institute of Information Science and the Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2765-5889","affiliations":[{"raw_affiliation_string":"Institute of Information Science and the Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884195","display_name":"Weibin Zhu","orcid":"https://orcid.org/0000-0002-7735-8778"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Zhu","raw_affiliation_strings":["Institute of Information Science and the Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7735-8778","affiliations":[{"raw_affiliation_string":"Institute of Information Science and the Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508981","display_name":"Yingying Gao","orcid":"https://orcid.org/0000-0002-7020-3028"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Gao","raw_affiliation_strings":["AI Center, China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Center, China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032367559","display_name":"Shilei Zhang","orcid":"https://orcid.org/0000-0001-8169-0098"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["AI Center, China Mobile Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Center, China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["AI Center, China Mobile Research Institute, Beijing, China","AI center, China Mobile Research Institute, Xichen District, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Center, China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"AI center, China Mobile Research Institute, Xichen District, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7714,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91364368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"2424","last_page":"2436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9923999905586243,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/monaural","display_name":"Monaural","score":0.8163979649543762},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.7407733201980591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7076860666275024},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.689979612827301},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6128240823745728},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6076215505599976},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5486441850662231},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.5380702614784241},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5164192318916321},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5164027810096741},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3760456442832947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22989043593406677},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1203363835811615},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07580581307411194},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0752129852771759}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8163979649543762},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.7407733201980591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7076860666275024},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.689979612827301},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6128240823745728},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6076215505599976},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5486441850662231},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.5380702614784241},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5164192318916321},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5164027810096741},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3760456442832947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22989043593406677},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1203363835811615},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07580581307411194},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0752129852771759},{"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3284522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284522","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W183625566","https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W2008806652","https://openalex.org/W2028138004","https://openalex.org/W2033310064","https://openalex.org/W2034040413","https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2100260186","https://openalex.org/W2103869314","https://openalex.org/W2130178255","https://openalex.org/W2131770202","https://openalex.org/W2135034868","https://openalex.org/W2137400100","https://openalex.org/W2149441837","https://openalex.org/W2151484683","https://openalex.org/W2164427415","https://openalex.org/W2194775991","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2516001803","https://openalex.org/W2605589342","https://openalex.org/W2718615637","https://openalex.org/W2892110446","https://openalex.org/W2940275453","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2998161426","https://openalex.org/W3015199127","https://openalex.org/W3026111682","https://openalex.org/W3096408984","https://openalex.org/W3097312999","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3111051109","https://openalex.org/W3120336970","https://openalex.org/W3160085755","https://openalex.org/W3161140524","https://openalex.org/W3162493033","https://openalex.org/W3197042120","https://openalex.org/W3197627016","https://openalex.org/W3205770165","https://openalex.org/W3206809722","https://openalex.org/W3213188934","https://openalex.org/W4221149546","https://openalex.org/W4221150474","https://openalex.org/W4221162870","https://openalex.org/W4224917453","https://openalex.org/W4224925070","https://openalex.org/W4224932531","https://openalex.org/W4224934178","https://openalex.org/W4225298533","https://openalex.org/W4225905067","https://openalex.org/W4283326514","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6738884980","https://openalex.org/W6739901393","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2042037691","https://openalex.org/W1107690805","https://openalex.org/W2082664927","https://openalex.org/W2097318409","https://openalex.org/W1978797160","https://openalex.org/W2739662815","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2946308721","https://openalex.org/W2056325840"],"abstract_inverted_index":{"To":[0],"further":[1],"improve":[2],"the":[3,6,23,44,50,66,81,84,93,99,104,145,168,175,180,185,191,195,208,226],"quality":[4],"of":[5,54,86,96,127,177,202,215,223],"enhanced":[7,134],"speech,":[8],"it":[9],"is":[10,78,117,150],"appealing":[11],"that":[12,167,184],"more":[13,136],"profound":[14],"articulatory":[15],"and":[16,34,101,156,173,188,217],"auditory":[17,161],"knowledge":[18],"should":[19],"be":[20,58],"introduced":[21],"into":[22],"speech":[24,32,40,97,123,135],"enhancement":[25,114],"model.":[26],"Among":[27],"these,":[28],"harmonics":[29,47,82,176],"seriously":[30],"affect":[31],"timbre":[33],"play":[35],"a":[36,110,140],"crucial":[37],"role":[38],"in":[39,43],"intelligibility.":[41],"Especially":[42],"frequency":[45],"domain,":[46],"appear":[48],"as":[49,62],"local":[51],"maximum":[52],"peaks":[53],"energy,":[55],"which":[56,119,152],"could":[57],"expected":[59],"to":[60,64,91,102,106,132],"serve":[61],"anchors":[63],"recover":[65,174],"distorted":[67],"speech.":[68,178],"In":[69,89,130],"this":[70],"paper,":[71],"an":[72],"explicit":[73],"modeling":[74],"method,":[75],"harmonic":[76,108,111,128,169],"attention,":[77],"presented,":[79],"patching":[80],"with":[83,124,138,159,207],"help":[85],"residual":[87],"ones.":[88],"order":[90],"maintain":[92],"spectral":[94],"structure":[95],"during":[98],"processing":[100],"enable":[103],"network":[105,115],"support":[107],"modeling,":[109],"attention-based":[112],"progressive":[113],"(HAPNet)":[116],"applied,":[118],"gradually":[120],"approaches":[121],"clean":[122],"stacked":[125],"modules":[126],"attention.":[129],"addition,":[131],"make":[133],"consistent":[137],"hearing,":[139],"loss":[141],"function":[142],"based":[143],"on":[144,199,212,220],"loudness":[146],"power":[147],"compression":[148],"(LC-SNR)":[149],"used,":[151],"measures":[153],"both":[154],"magnitude":[155],"phase":[157],"values":[158],"appropriate":[160],"effects.":[162],"The":[163],"experimental":[164],"visualization":[165],"indicates":[166],"attention":[170],"can":[171],"capture":[172],"And":[179],"objective":[181],"evaluations":[182],"show":[183],"presented":[186,196],"HAPNet":[187],"LC-SNR":[189],"outperform":[190],"referenced":[192,209],"methods.":[193],"Furthermore,":[194],"model":[197],"trained":[198,211,219],"100":[200],"hours":[201,214,222],"data":[203,224],"achieves":[204],"competitive":[205],"results":[206],"models":[210],"3000+":[213],"data,":[216],"one":[218],"500":[221],"yields":[225],"state-of-the-art":[227],"performance.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":12}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}