{"id":"https://openalex.org/W4224932531","doi":"https://doi.org/10.1109/icassp43922.2022.9746610","title":"Multi-Scale Temporal Frequency Convolutional Network With Axial Attention for Speech Enhancement","display_name":"Multi-Scale Temporal Frequency Convolutional Network With Axial Attention for Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932531","doi":"https://doi.org/10.1109/icassp43922.2022.9746610"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746610","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/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":"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":"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":6.129,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97630332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9122","last_page":"9126"},"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":0.9984999895095825,"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":0.995199978351593,"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/reverberation","display_name":"Reverberation","score":0.7594242691993713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456052303314209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7156087756156921},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5994624495506287},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5810277462005615},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.568571150302887},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5333483219146729},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49897122383117676},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.47221070528030396},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.46406373381614685},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44991421699523926},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43970435857772827},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4319063723087311},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42244553565979004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39217472076416016},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3201708197593689},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20520037412643433},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.147533118724823},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07483446598052979},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.06731417775154114}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7594242691993713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456052303314209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7156087756156921},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5994624495506287},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5810277462005615},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.568571150302887},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5333483219146729},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49897122383117676},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.47221070528030396},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.46406373381614685},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44991421699523926},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43970435857772827},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4319063723087311},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42244553565979004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39217472076416016},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3201708197593689},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20520037412643433},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.147533118724823},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07483446598052979},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.06731417775154114},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746610","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2046317813","https://openalex.org/W2065804682","https://openalex.org/W2099464104","https://openalex.org/W2131108018","https://openalex.org/W2158582019","https://openalex.org/W2898268964","https://openalex.org/W2952218014","https://openalex.org/W2974407961","https://openalex.org/W3092864146","https://openalex.org/W3095248373","https://openalex.org/W3097034112","https://openalex.org/W3099330747","https://openalex.org/W3101330598","https://openalex.org/W3104196160","https://openalex.org/W3113290170","https://openalex.org/W3120336970","https://openalex.org/W3138516171","https://openalex.org/W3160085755","https://openalex.org/W3160129476","https://openalex.org/W3162348042","https://openalex.org/W3209141406","https://openalex.org/W4224919230","https://openalex.org/W4225905067","https://openalex.org/W6679212047","https://openalex.org/W6787607767","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W2156393451","https://openalex.org/W2185164075","https://openalex.org/W2899955959","https://openalex.org/W2140365942","https://openalex.org/W1954839664","https://openalex.org/W2136599659","https://openalex.org/W1503085383","https://openalex.org/W1491017269","https://openalex.org/W2118159520","https://openalex.org/W2130361043"],"abstract_inverted_index":{"Speech":[0],"quality":[1],"is":[2,53],"often":[3],"degraded":[4],"by":[5],"acoustic":[6,50],"echoes,":[7,29],"background":[8],"noise,":[9,30],"and":[10,23,31,75,82,96,118],"reverberation.":[11,32],"In":[12,104],"this":[13,106],"paper,":[14],"we":[15,37],"propose":[16],"a":[17,39,48,73],"system":[18,90],"consisting":[19],"of":[20,65,101],"deep":[21,35,59],"learning":[22],"signal":[24,46],"processing":[25],"to":[26,112],"simultaneously":[27],"suppress":[28],"For":[33,44],"the":[34,45,63,66,113],"learning,":[36],"design":[38],"novel":[40],"speech":[41,67,115],"dense-prediction":[42,68],"backbone.":[43],"processing,":[47,81],"linear":[49],"echo":[51],"canceller":[52],"used":[54],"as":[55,72],"conditional":[56],"information":[57],"for":[58],"learning.":[60],"To":[61],"improve":[62],"performance":[64],"backbone,":[69],"strategies":[70],"such":[71],"microphone":[74],"reference":[76],"phase":[77],"encoder,":[78],"multi-scale":[79],"time-frequency":[80],"streaming":[83],"axial":[84],"attention":[85],"are":[86],"designed.":[87],"The":[88],"proposed":[89],"ranked":[91],"first":[92],"in":[93,121],"both":[94],"AEC":[95],"DNS":[97],"Challenge":[98,125],"(non-personal":[99],"track)":[100],"ICASSP":[102,122],"2022.":[103],"addition,":[105],"backbone":[107],"has":[108],"also":[109],"been":[110],"extended":[111],"multi-channel":[114],"enhancement":[116],"task,":[117],"placed":[119],"second":[120],"2022":[123],"L3DAS22":[124],"<sup":[126],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[128],".":[129]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}