{"id":"https://openalex.org/W4392902507","doi":"https://doi.org/10.1109/icassp48485.2024.10445944","title":"Hybrid Attention Time-Frequency Analysis Network for Single-Channel Speech Enhancement","display_name":"Hybrid Attention Time-Frequency Analysis Network for Single-Channel Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902507","doi":"https://doi.org/10.1109/icassp48485.2024.10445944"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5090668921","display_name":"Zehua Zhang","orcid":"https://orcid.org/0000-0003-3215-5317"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008366157","display_name":"Xingwei Liang","orcid":"https://orcid.org/0000-0002-5940-3440"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Liang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026719663","display_name":"Ruifeng Xu","orcid":"https://orcid.org/0000-0002-4009-5679"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifeng Xu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651653","display_name":"Mingjiang Wang","orcid":"https://orcid.org/0000-0002-4706-009X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjiang Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10426","last_page":"10430"},"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":0.9990000128746033,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7525938749313354},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6867804527282715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5933329463005066},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5186706781387329},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5097793936729431},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4921385645866394},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48790881037712097},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.47181475162506104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4434872269630432},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43825098872184753},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4080420136451721},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4007090628147125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36431318521499634},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16446945071220398}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525938749313354},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6867804527282715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5933329463005066},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5186706781387329},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5097793936729431},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4921385645866394},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48790881037712097},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.47181475162506104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4434872269630432},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43825098872184753},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4080420136451721},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4007090628147125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36431318521499634},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16446945071220398},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2006129368","https://openalex.org/W2027804983","https://openalex.org/W2070126272","https://openalex.org/W2094721231","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2950116990","https://openalex.org/W2952218014","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W2998445964","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3109394096","https://openalex.org/W3134695619","https://openalex.org/W3138516171","https://openalex.org/W3161950572","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3206809722","https://openalex.org/W3213188934","https://openalex.org/W4312678820","https://openalex.org/W4372267368","https://openalex.org/W4375869466","https://openalex.org/W6786372312","https://openalex.org/W6796417832"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"The":[0,90],"time-frequency":[1,24],"domain":[2],"remains":[3],"central":[4],"to":[5,44,63,84],"the":[6,11,29,47,52,111,126],"speech":[7,16],"signal":[8],"analysis.":[9],"Enhancing":[10],"efficacy":[12],"of":[13,23,92,114],"neural":[14],"network-based":[15],"models":[17],"demands":[18],"a":[19,41],"detailed":[20],"multi-scale":[21],"analysis":[22],"features.":[25],"This":[26],"study":[27],"presents":[28],"Hybrid":[30,59],"Attention":[31,60],"Time-Frequency":[32],"Analysis":[33],"Network":[34],"(HATFANet),":[35],"an":[36],"innovative":[37],"model":[38],"that":[39],"uses":[40],"dual-branch":[42],"structure":[43],"concurrently":[45],"estimate":[46],"ideal":[48],"ratio":[49],"mask":[50],"and":[51,67,80,96,105,137],"enhanced":[53],"complex":[54],"spectrum.":[55],"Each":[56],"branch":[57],"incorporates":[58],"Blocks":[61],"(HABs)":[62],"capture":[64],"local,":[65],"global,":[66],"inter-window":[68],"attention":[69,88,95,103],"for":[70],"more":[71],"effective":[72],"deep":[73],"feature":[74],"extraction":[75],"by":[76],"employing":[77],"reshaping":[78],"techniques":[79],"gated":[81],"multi-layer":[82],"perceptrons":[83],"focus":[85],"on":[86,125],"different":[87],"scales.":[89,120],"addition":[91],"residual":[93],"channel":[94,102],"window":[97],"multi-head":[98],"self-attention":[99],"mechanism":[100],"accentuate":[101],"features":[104],"intra-window":[106],"attention.":[107],"Our":[108],"experiments":[109],"verify":[110],"pivotal":[112],"role":[113],"these":[115],"HABs":[116],"across":[117],"varied":[118],"attentional":[119],"HATFANet":[121],"achieves":[122],"state-of-the-art":[123],"results":[124],"Voice":[127],"Bank":[128],"+":[129],"DEMAND":[130],"dataset,":[131],"recording":[132],"3.37":[133],"PESQ,":[134],"95.8%":[135],"STOI,":[136],"10.15":[138],"SSNR.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}