{"id":"https://openalex.org/W4393241238","doi":"https://doi.org/10.1109/taslp.2024.3382426","title":"Adjustable Coherent-to-Diffuse Power Estimator for Binaural Speech Enhancement in Multi-Talker Environments","display_name":"Adjustable Coherent-to-Diffuse Power Estimator for Binaural Speech Enhancement in Multi-Talker Environments","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393241238","doi":"https://doi.org/10.1109/taslp.2024.3382426"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3382426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3382426","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5056519652","display_name":"Reza Ghanavi","orcid":"https://orcid.org/0000-0001-8078-9707"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Reza Ghanavi","raw_affiliation_strings":["Computing and Audio Research Laboratory (CARLab), School of electrical and computer engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Computing and Audio Research Laboratory (CARLab), School of electrical and computer engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101410599","display_name":"Craig Jin","orcid":"https://orcid.org/0000-0003-4636-753X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Craig T. Jin","raw_affiliation_strings":["Computing and Audio Research Laboratory (CARLab), School of electrical and computer engineering, The University of Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Computing and Audio Research Laboratory (CARLab), School of electrical and computer engineering, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056519652"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.3504,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48877925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2312","last_page":"2323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9847000241279602,"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":0.9442999958992004,"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/estimator","display_name":"Estimator","score":0.6470010280609131},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6406408548355103},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.6164073944091797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4356253147125244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38322579860687256},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3617260158061981},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.23937124013900757},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22622355818748474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20138052105903625},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13451731204986572},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13362771272659302}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6470010280609131},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6406408548355103},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.6164073944091797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4356253147125244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38322579860687256},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3617260158061981},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.23937124013900757},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22622355818748474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20138052105903625},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13451731204986572},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13362771272659302}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3382426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3382426","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1536891161","https://openalex.org/W1552314771","https://openalex.org/W1572964346","https://openalex.org/W1967612008","https://openalex.org/W1977949126","https://openalex.org/W1986423218","https://openalex.org/W1998648683","https://openalex.org/W2013139519","https://openalex.org/W2015775032","https://openalex.org/W2016102878","https://openalex.org/W2028111967","https://openalex.org/W2030486566","https://openalex.org/W2033990903","https://openalex.org/W2041733487","https://openalex.org/W2044658503","https://openalex.org/W2047685023","https://openalex.org/W2071776579","https://openalex.org/W2080145918","https://openalex.org/W2104695149","https://openalex.org/W2122171611","https://openalex.org/W2125114513","https://openalex.org/W2126641873","https://openalex.org/W2127911452","https://openalex.org/W2128974165","https://openalex.org/W2136682440","https://openalex.org/W2141998673","https://openalex.org/W2143156057","https://openalex.org/W2144980666","https://openalex.org/W2149693148","https://openalex.org/W2166547995","https://openalex.org/W2185519759","https://openalex.org/W2460742184","https://openalex.org/W2578531100","https://openalex.org/W2784210009","https://openalex.org/W2794289187","https://openalex.org/W2935873029","https://openalex.org/W2945449954","https://openalex.org/W2963454081","https://openalex.org/W3017760774","https://openalex.org/W3116150930","https://openalex.org/W3161643320","https://openalex.org/W6683785785","https://openalex.org/W6686463753","https://openalex.org/W6703471520"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2026165661","https://openalex.org/W1979944951","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"The":[0],"binaural":[1,30,48,97,112,151],"coherence-to-diffuse":[2],"power":[3],"ratio":[4],"(CDR)":[5],"estimate":[6],"in":[7,12,119,153],"reverberant":[8],"environments":[9],"is":[10,35],"essential":[11],"many":[13],"speech":[14,118],"enhancement":[15],"algorithms":[16],"applied":[17],"within":[18],"hear-through":[19],"systems.":[20],"In":[21],"this":[22],"work,":[23],"we":[24],"propose":[25],"a":[26,38,96],"parameterised":[27],"and":[28,89,114,121,125,135],"adjustable":[29,139],"CDR":[31,52,80,105],"estimator":[32,81,106],"whose":[33],"formulation":[34],"based":[36],"on":[37,66,84],"geometrical":[39],"interpretation":[40],"of":[41,60,70,95,116,149],"the":[42,56,61,71,85,92,103,138,145,150],"short-time":[43],"complex":[44],"coherence":[45,68,88],"function":[46],"between":[47],"microphone":[49],"signals.":[50],"Conventional":[51],"estimators":[53],"often":[54,128],"distort":[55],"natural":[57,93],"spectro-temporal":[58],"behaviour":[59],"noise":[62,76,98],"field":[63],"by":[64],"relying":[65],"theoretical":[67],"models":[69],"desired":[72],"signal":[73],"and/or":[74],"diffuse":[75],"field.":[77,99],"Our":[78],"proposed":[79,104],"relies":[82],"only":[83],"observed":[86],"spatial":[87],"better":[90],"preserves":[91],"characteristics":[94],"We":[100],"demonstrate":[101],"that":[102,126],"can":[107],"be":[108],"used":[109],"effectively":[110],"for":[111,133],"dereverberation":[113,134],"denoising":[115],"broadside":[117],"multi-talker":[120],"noisy":[122],"acoustic":[123],"conditions":[124],"it":[127],"outperforms":[129],"state-of-the-art":[130],"coherence-based":[131],"methods":[132],"denoising.":[136],"Furthermore,":[137],"parameter":[140],"enables":[141],"one":[142],"to":[143],"minimise":[144],"frequency-dependent":[146],"estimation":[147],"error":[148],"system":[152],"different":[154],"environments.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}