{"id":"https://openalex.org/W3214515055","doi":"https://doi.org/10.1109/icassp43922.2022.9746454","title":"Time-Frequency Attention for Monaural Speech Enhancement","display_name":"Time-Frequency Attention for Monaural Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3214515055","doi":"https://doi.org/10.1109/icassp43922.2022.9746454","mag":"3214515055"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746454","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":"conference-paper","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/A5042675934","display_name":"Qiquan Zhang","orcid":"https://orcid.org/0000-0001-5089-6317"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qiquan Zhang","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748969","display_name":"Qi Song","orcid":"https://orcid.org/0000-0002-1726-7858"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta AI,United States","Meta AI, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,United States","institution_ids":["https://openalex.org/I2799847335"]},{"raw_affiliation_string":"Meta AI, United States","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041494929","display_name":"Aaron Nicolson","orcid":"https://orcid.org/0000-0002-7163-1809"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I4210141844","display_name":"Australian e-Health Research Centre","ror":"https://ror.org/04ywhbc61","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801244131","https://openalex.org/I2801453606","https://openalex.org/I4210141844","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aaron Nicolson","raw_affiliation_strings":["CSIRO,Australian e-Health Research Centre,Australia","Australian e-Health Research Centre, CSIRO, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO,Australian e-Health Research Centre,Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I4210141844"]},{"raw_affiliation_string":"Australian e-Health Research Centre, CSIRO, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I4210141844"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Chinese University of Hong Kong, Shenzhen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7852","last_page":"7856"},"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.7430433034896851},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7387627959251404},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7322686910629272},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7158843278884888},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6797197461128235},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.668060839176178},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6309565305709839},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6069676280021667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5180525779724121},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5012125968933105},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4261263906955719},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38293054699897766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33474892377853394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27986329793930054},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24382421374320984},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19094255566596985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.147599995136261},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09432452917098999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430433034896851},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7387627959251404},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7322686910629272},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7158843278884888},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6797197461128235},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.668060839176178},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6309565305709839},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6069676280021667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5180525779724121},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5012125968933105},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4261263906955719},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38293054699897766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33474892377853394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27986329793930054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24382421374320984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19094255566596985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.147599995136261},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09432452917098999},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"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/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746454","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"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/426296","is_oa":false,"landing_page_url":"http://hdl.handle.net/10072/426296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8700000047683716,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1506438021","https://openalex.org/W1522301498","https://openalex.org/W2038484192","https://openalex.org/W2069681747","https://openalex.org/W2121973264","https://openalex.org/W2144404214","https://openalex.org/W2219249508","https://openalex.org/W2291877678","https://openalex.org/W2396174604","https://openalex.org/W2516001803","https://openalex.org/W2539238457","https://openalex.org/W2678916739","https://openalex.org/W2752782242","https://openalex.org/W2792764867","https://openalex.org/W2884585870","https://openalex.org/W2889118710","https://openalex.org/W2897371647","https://openalex.org/W2914067823","https://openalex.org/W2937484199","https://openalex.org/W2950962438","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W3017350693","https://openalex.org/W3026111682","https://openalex.org/W3095820034","https://openalex.org/W3098606562","https://openalex.org/W3099330747","https://openalex.org/W3103334733","https://openalex.org/W3147539069","https://openalex.org/W3197822518","https://openalex.org/W4253928870","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6712099205","https://openalex.org/W6739901393","https://openalex.org/W6749825310","https://openalex.org/W6753412334"],"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/W2072124114","https://openalex.org/W2538939196","https://openalex.org/W3045520545"],"abstract_inverted_index":{"Most":[0],"studies":[1],"on":[2,84],"speech":[3,13],"enhancement":[4],"generally":[5],"don’t":[6],"explicitly":[7],"consider":[8],"the":[9,53,61,70,77,100,118,122],"energy":[10],"distribution":[11],"of":[12,24,56,63,104],"in":[14,102],"time-frequency":[15],"(T-F)":[16],"representation,":[17],"which":[18],"is":[19,46],"important":[20],"for":[21],"accurate":[22],"prediction":[23],"mask":[25],"or":[26],"spectra.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,68],"present":[32],"a":[33,42,131],"simple":[34],"yet":[35],"effective":[36],"T-F":[37,57],"attention":[38,44],"(TFA)":[39],"module,":[40,67],"where":[41],"2-D":[43],"map":[45],"produced":[47],"to":[48,52],"provide":[49],"differentiated":[50],"weights":[51],"spectral":[54],"components":[55],"representation.":[58],"To":[59],"validate":[60],"effectiveness":[62],"our":[64,95],"proposed":[65,119],"TFA":[66,96,123],"use":[69],"residual":[71],"temporal":[72],"convolution":[73],"network":[74,79],"(ResTCN)":[75],"as":[76],"backbone":[78],"and":[80],"conduct":[81],"extensive":[82],"experiments":[83,91],"two":[85],"commonly":[86],"used":[87],"training":[88],"targets.":[89],"Our":[90],"demonstrate":[92],"that":[93,117],"applying":[94],"module":[97,124],"significantly":[98],"improves":[99],"performance":[101],"terms":[103],"five":[105],"objective":[106],"evaluation":[107,114],"metrics":[108],"with":[109,121],"negligible":[110],"parameter":[111],"overhead.":[112],"The":[113],"results":[115],"show":[116],"ResTCN":[120],"(ResTCN+TFA)":[125],"consistently":[126],"outperforms":[127],"other":[128],"baselines":[129],"by":[130],"large":[132],"margin.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}