{"id":"https://openalex.org/W4224931234","doi":"https://doi.org/10.1109/icassp43922.2022.9746902","title":"Multi-Scale Temporal Frequency Convolutional Network with Axial Attention for Multi-Channel Speech Enhancement","display_name":"Multi-Scale Temporal Frequency Convolutional Network with Axial Attention for Multi-Channel Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931234","doi":"https://doi.org/10.1109/icassp43922.2022.9746902"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746902","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5073038439","display_name":"Guochang Zhang","orcid":"https://orcid.org/0000-0001-6695-9968"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guochang Zhang","raw_affiliation_strings":["Baidu Inc,Department of Speech Technology,Beijing,China,100085"],"affiliations":[{"raw_affiliation_string":"Baidu Inc,Department of Speech Technology,Beijing,China,100085","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109538889","display_name":"Chunliang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunliang Wang","raw_affiliation_strings":["Baidu Inc,Department of Speech Technology,Beijing,China,100085"],"affiliations":[{"raw_affiliation_string":"Baidu Inc,Department of Speech Technology,Beijing,China,100085","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013721090","display_name":"Libiao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libiao Yu","raw_affiliation_strings":["Baidu Inc,Department of Speech Technology,Beijing,China,100085"],"affiliations":[{"raw_affiliation_string":"Baidu Inc,Department of Speech Technology,Beijing,China,100085","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067500170","display_name":"Jianqiang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Wei","raw_affiliation_strings":["Baidu Inc,Department of Speech Technology,Beijing,China,100085"],"affiliations":[{"raw_affiliation_string":"Baidu Inc,Department of Speech Technology,Beijing,China,100085","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073038439"],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":2.322,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90900504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9206","last_page":"9210"},"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":0.9966999888420105,"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/T11309","display_name":"Music and Audio Processing","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6739813089370728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6718758344650269},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5949231386184692},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4514934718608856},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44905662536621094},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4239053726196289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3820597231388092},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3392619490623474},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14994603395462036},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14285242557525635},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09997954964637756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6739813089370728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6718758344650269},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5949231386184692},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4514934718608856},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44905662536621094},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4239053726196289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3820597231388092},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3392619490623474},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14994603395462036},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14285242557525635},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09997954964637756},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746902","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2398042854","https://openalex.org/W2407277936","https://openalex.org/W2952218014","https://openalex.org/W2963868408","https://openalex.org/W2974407961","https://openalex.org/W3036601975","https://openalex.org/W3092864146","https://openalex.org/W3094502228","https://openalex.org/W3095248373","https://openalex.org/W3099330747","https://openalex.org/W3101330598","https://openalex.org/W3113290170","https://openalex.org/W3120336970","https://openalex.org/W3138516171","https://openalex.org/W3160129476","https://openalex.org/W3162341667","https://openalex.org/W3170405627","https://openalex.org/W3196940724","https://openalex.org/W4221152722","https://openalex.org/W4225270933","https://openalex.org/W6780218876","https://openalex.org/W6787607767","https://openalex.org/W6797037654","https://openalex.org/W6800489933"],"related_works":["https://openalex.org/W1600259599","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2142795561","https://openalex.org/W2379948177","https://openalex.org/W2107949441","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"Speech":[0],"quality":[1],"is":[2,15,30,42,79,118],"often":[3],"degraded":[4],"by":[5,102],"background":[6],"noise":[7],"and":[8,38,71,109,125,136],"reverberation.":[9],"Usually,":[10],"a":[11,24,103],"dense":[12],"prediction":[13],"network":[14],"used":[16,43,120],"to":[17],"reconstruct":[18],"clean":[19],"speech.":[20],"In":[21],"this":[22,40,50],"work,":[23],"novel":[25],"backbone":[26,41,117],"for":[27,44,121],"speech":[28,46,123],"dense-prediction":[29],"proposed.":[31],"After":[32],"adjusting":[33],"part":[34],"of":[35,56,85],"the":[36,54,57,83,95],"input":[37],"output,":[39],"multi-channel":[45,62],"enhancement":[47,124],"task":[48],"in":[49,112,128],"paper.":[51],"To":[52],"improve":[53],"performance":[55],"backbone,":[58],"strategies":[59],"such":[60],"as":[61],"phase":[63],"encoder,":[64],"multi-scale":[65],"temporal":[66],"frequency":[67],"processing,":[68],"axial":[69],"self-attention,":[70],"two-stage":[72],"masking":[73],"are":[74],"designed.":[75],"Our":[76],"proposed":[77,96,116],"method":[78,97],"evaluated":[80],"based":[81],"on":[82],"datasets":[84],"ICASSP":[86,130],"2022":[87,131],"L3DAS22":[88,113],"Challenge.":[89,114],"The":[90,115],"experimental":[91],"results":[92],"show":[93],"that":[94],"outperforms":[98],"previous":[99],"state-of-the-art":[100],"baselines":[101],"large":[104],"margin":[105],"<sup":[106,133,140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107,134,141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[108],"ranked":[110,126],"second":[111],"also":[119],"mono-channel":[122],"first":[127],"both":[129],"AEC":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[135],"DNS":[137],"Challenges(non-personal":[138],"track)":[139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>":[142],".":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":12}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}