{"id":"https://openalex.org/W4392911133","doi":"https://doi.org/10.1109/icassp48485.2024.10447090","title":"Binaural Speech Enhancement Using Deep Complex Convolutional Transformer Networks","display_name":"Binaural Speech Enhancement Using Deep Complex Convolutional Transformer Networks","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392911133","doi":"https://doi.org/10.1109/icassp48485.2024.10447090"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447090","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":"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/A5054378384","display_name":"Vikas Tokala","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vikas Tokala","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011673214","display_name":"Eric Grinstein","orcid":"https://orcid.org/0000-0003-4502-5407"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eric Grinstein","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004899548","display_name":"Mike Brookes","orcid":"https://orcid.org/0000-0001-7105-4936"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mike Brookes","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062526199","display_name":"Simon Doclo","orcid":"https://orcid.org/0000-0002-3392-2381"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Doclo","raw_affiliation_strings":["University of Oldenburg,Department of Medical Physics and Acoustics,Germany","Department of Medical Physics and Acoustics, University of Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oldenburg,Department of Medical Physics and Acoustics,Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Department of Medical Physics and Acoustics, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]},{"id":"https://openalex.org/I4210091381","display_name":"William Demant Holding (Denmark)","ror":"https://ror.org/00an7pj80","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210091381"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Demant A/S,Sm&#x00F8;rum,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Demant A/S,Sm&#x00F8;rum,Denmark","institution_ids":["https://openalex.org/I4210091381"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,UK","Department of Electrical and Electronic Engineering, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054378384"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":4.2247,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94809193,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"685"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.9186817407608032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7694409489631653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.675156831741333},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6323515176773071},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.49314969778060913},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46241331100463867},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45948538184165955},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4455488622188568},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4262527823448181},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.4106464385986328},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3883647322654724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32424670457839966},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2897774279117584},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.1433747410774231},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12127384543418884}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.9186817407608032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694409489631653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.675156831741333},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6323515176773071},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.49314969778060913},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46241331100463867},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45948538184165955},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4455488622188568},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4262527823448181},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.4106464385986328},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3883647322654724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32424670457839966},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2897774279117584},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.1433747410774231},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12127384543418884},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447090","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"},{"id":"pmh:oai:pure.atira.dk:publications/ebdc6d91-8ae6-4a2e-9197-c2c8c4e8ec40","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/ebdc6d91-8ae6-4a2e-9197-c2c8c4e8ec40","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tokala, V, Grinstein, E, Brookes, M, Doclo, S, Jensen, J & Naylor, P A 2024, Binaural Speech Enhancement Using Deep Complex Convolutional Transformer Networks. in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. IEEE (Institute of Electrical and Electronics Engineers), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 681-685, 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024, Seoul, Korea, Republic of, 14/04/2024. https://doi.org/10.1109/ICASSP48485.2024.10447090","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5952785084","display_name":"Environment and Listener Optimised Speech Processing for Hearing Enhancement in Real Situations (ELO-SPHERES)","funder_award_id":"EP/S035842/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7537482475","display_name":null,"funder_award_id":"956369","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1516457120","https://openalex.org/W1974387177","https://openalex.org/W2009649672","https://openalex.org/W2067295501","https://openalex.org/W2077090930","https://openalex.org/W2098882755","https://openalex.org/W2128974165","https://openalex.org/W2291877678","https://openalex.org/W2539508298","https://openalex.org/W2810434345","https://openalex.org/W2889442120","https://openalex.org/W2900251640","https://openalex.org/W2952218014","https://openalex.org/W2963452667","https://openalex.org/W2998161426","https://openalex.org/W3015279216","https://openalex.org/W3016129867","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3127686677","https://openalex.org/W4233385860","https://openalex.org/W4312251618","https://openalex.org/W4312701366","https://openalex.org/W4385245566","https://openalex.org/W6738884980","https://openalex.org/W6751512325","https://openalex.org/W6772349387"],"related_works":["https://openalex.org/W1991848873","https://openalex.org/W4377018054","https://openalex.org/W2005888073","https://openalex.org/W3004570917","https://openalex.org/W2337758134","https://openalex.org/W2022765019","https://openalex.org/W4389240440","https://openalex.org/W2084430325","https://openalex.org/W4244700398","https://openalex.org/W2041661331"],"abstract_inverted_index":{"Studies":[0],"have":[1],"shown":[2],"that":[3,83,115],"in":[4,60,131],"noisy":[5],"acoustic":[6,101],"environments,":[7],"providing":[8],"binaural":[9,30,71,122,128],"signals":[10],"to":[11,54],"the":[12,61,65,85,116,120,127],"user":[13],"of":[14,70,87,111],"an":[15,41],"assistive":[16],"listening":[17],"device":[18],"may":[19],"improve":[20],"speech":[21,31,92,123],"intelligibility":[22,93,124],"and":[23,44,67,95,108,125],"spatial":[24,88],"awareness.":[25],"This":[26],"paper":[27],"presents":[28],"a":[29,35,45,79,104],"enhancement":[32],"method":[33,118],"using":[34,78],"complex":[36,46,57],"convolutional":[37],"neural":[38],"network":[39],"with":[40,91,103,133],"encoder-decoder":[42],"architecture":[43],"multi-head":[47],"attention":[48],"transformer.":[49],"The":[50,74],"model":[51,75],"is":[52,76],"trained":[53,77],"estimate":[55],"individual":[56],"ratio":[58],"masks":[59],"time-frequency":[62],"domain":[63],"for":[64,100],"left":[66],"right-ear":[68],"channels":[69],"hearing":[72],"devices.":[73],"novel":[80],"loss":[81],"function":[82],"incorporates":[84],"preservation":[86],"information":[89],"along":[90],"improvement":[94],"noise":[96,110],"reduction.":[97],"Simulation":[98],"results":[99],"scenarios":[102],"single":[105],"target":[106],"speaker":[107],"isotropic":[109],"various":[112],"types":[113],"show":[114],"proposed":[117],"improves":[119],"estimated":[121],"preserves":[126],"cues":[129],"better":[130],"comparison":[132],"several":[134],"baseline":[135],"algorithms.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
