{"id":"https://openalex.org/W4392114345","doi":"https://doi.org/10.1109/taslp.2024.3369531","title":"Channel-Combination Algorithms for Robust Distant Voice Activity and Overlapped Speech Detection","display_name":"Channel-Combination Algorithms for Robust Distant Voice Activity and Overlapped Speech Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392114345","doi":"https://doi.org/10.1109/taslp.2024.3369531"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3369531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3369531","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/A5036816609","display_name":"Th\u00e9o Mariotte","orcid":"https://orcid.org/0000-0002-2108-101X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210132387","display_name":"Institut des Mol\u00e9cules et Mat\u00e9riaux du Mans","ror":"https://ror.org/03a9gd656","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210108471","https://openalex.org/I4210128300","https://openalex.org/I4210132387"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Th\u00e9o Mariotte","raw_affiliation_strings":["Laboratoire d'Acoustique de l'Université du Mans (LAUM), UMR 6613, Institut d'Acoustique - Graduate School (IA-GS), CNRS, Le Mans Université, Le Mans, France"],"raw_orcid":"https://orcid.org/0000-0002-2108-101X","affiliations":[{"raw_affiliation_string":"Laboratoire d'Acoustique de l'Université du Mans (LAUM), UMR 6613, Institut d'Acoustique - Graduate School (IA-GS), CNRS, Le Mans Université, Le Mans, France","institution_ids":["https://openalex.org/I4210132387","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002979461","display_name":"Anthony Larcher","orcid":"https://orcid.org/0000-0003-4398-0224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anthony Larcher","raw_affiliation_strings":["Institut Claude Chappe, Laboratoire d'Acoustique de l'Université du Mans (LAUM), Le Mans, France"],"raw_orcid":"https://orcid.org/0000-0003-4398-0224","affiliations":[{"raw_affiliation_string":"Institut Claude Chappe, Laboratoire d'Acoustique de l'Université du Mans (LAUM), Le Mans, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032144114","display_name":"Silvio Montr\u00e9sor","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210132387","display_name":"Institut des Mol\u00e9cules et Mat\u00e9riaux du Mans","ror":"https://ror.org/03a9gd656","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210108471","https://openalex.org/I4210128300","https://openalex.org/I4210132387"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Silvio Montr\u00e9sor","raw_affiliation_strings":["Laboratoire d'Acoustique de l'Université du Mans (LAUM), UMR 6613, Institut d'Acoustique - Graduate School (IA-GS), CNRS, Le Mans Université, Le Mans, France"],"raw_orcid":"https://orcid.org/0000-0002-1493-1637","affiliations":[{"raw_affiliation_string":"Laboratoire d'Acoustique de l'Université du Mans (LAUM), UMR 6613, Institut d'Acoustique - Graduate School (IA-GS), CNRS, Le Mans Université, Le Mans, France","institution_ids":["https://openalex.org/I4210132387","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103246472","display_name":"Jean\u2010Hugh Thomas","orcid":"https://orcid.org/0000-0003-3512-214X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210132387","display_name":"Institut des Mol\u00e9cules et Mat\u00e9riaux du Mans","ror":"https://ror.org/03a9gd656","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210108471","https://openalex.org/I4210128300","https://openalex.org/I4210132387"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Hugh Thomas","raw_affiliation_strings":["Laboratoire d'Acoustique de l'Université du Mans (LAUM), UMR 6613, Institut d'Acoustique - Graduate School (IA-GS), CNRS, Le Mans Université, Le Mans, France"],"raw_orcid":"https://orcid.org/0000-0003-3512-214X","affiliations":[{"raw_affiliation_string":"Laboratoire d'Acoustique de l'Université du Mans (LAUM), UMR 6613, Institut d'Acoustique - Graduate School (IA-GS), CNRS, Le Mans Université, Le Mans, France","institution_ids":["https://openalex.org/I4210132387","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036816609"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210132387"],"apc_list":null,"apc_paid":null,"fwci":1.9729,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85908922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1859","last_page":"1872"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7451854944229126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6328622102737427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6013683676719666},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.531943142414093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49548637866973877},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25718528032302856},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1809733808040619}],"concepts":[{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7451854944229126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6328622102737427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6013683676719666},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.531943142414093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49548637866973877},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25718528032302856},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1809733808040619}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3369531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3369531","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W15516501","https://openalex.org/W36345725","https://openalex.org/W1522301498","https://openalex.org/W1946893126","https://openalex.org/W2009876684","https://openalex.org/W2032362923","https://openalex.org/W2059203007","https://openalex.org/W2061074721","https://openalex.org/W2097583714","https://openalex.org/W2125336414","https://openalex.org/W2129120544","https://openalex.org/W2136745572","https://openalex.org/W2148613904","https://openalex.org/W2166547995","https://openalex.org/W2168729028","https://openalex.org/W2170644918","https://openalex.org/W2402428045","https://openalex.org/W2403186097","https://openalex.org/W2406262283","https://openalex.org/W2406713305","https://openalex.org/W2499102192","https://openalex.org/W2552290276","https://openalex.org/W2589857635","https://openalex.org/W2767895109","https://openalex.org/W2797412426","https://openalex.org/W2803322398","https://openalex.org/W2891247151","https://openalex.org/W2898395910","https://openalex.org/W2909607850","https://openalex.org/W2921496354","https://openalex.org/W2968071640","https://openalex.org/W2981728176","https://openalex.org/W2989863749","https://openalex.org/W3004940340","https://openalex.org/W3007258144","https://openalex.org/W3015372568","https://openalex.org/W3015527782","https://openalex.org/W3015780472","https://openalex.org/W3015783745","https://openalex.org/W3016257794","https://openalex.org/W3016912202","https://openalex.org/W3020336359","https://openalex.org/W3045742579","https://openalex.org/W3097148135","https://openalex.org/W3100336094","https://openalex.org/W3132182240","https://openalex.org/W3162899647","https://openalex.org/W3178462146","https://openalex.org/W3196595845","https://openalex.org/W3198134544","https://openalex.org/W3198827946","https://openalex.org/W3203236698","https://openalex.org/W3207834622","https://openalex.org/W3211779545","https://openalex.org/W3212886388","https://openalex.org/W4206633762","https://openalex.org/W4252183610","https://openalex.org/W4283836186","https://openalex.org/W4385245566","https://openalex.org/W4385823318","https://openalex.org/W6631190155","https://openalex.org/W6784406610","https://openalex.org/W6838434699"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067"],"abstract_inverted_index":{"Voice":[0],"Activity":[1],"Detection":[2,7],"(VAD)":[3],"and":[4,52,64,115,141],"Overlapped":[5],"Speech":[6],"(OSD)":[8],"are":[9,131,149],"key":[10],"pre-processing":[11],"tasks":[12],"for":[13],"speaker":[14,139],"diarization.":[15],"In":[16],"the":[17,74,82,87,101,108,117,134,184,197],"meeting":[18,89],"context,":[19],"it":[20],"is":[21,174],"often":[22],"easier":[23],"to":[24,35,46,161,176],"capture":[25],"speech":[26,103],"with":[27],"a":[28,41,152,178],"distant":[29,48,102],"device.":[30],"This":[31,55],"consideration":[32],"however":[33],"leads":[34],"severe":[36],"performance":[37],"degradation.":[38],"We":[39,68],"study":[40],"unified":[42],"supervised":[43],"learning":[44],"framework":[45],"solve":[47],"multi-microphone":[49],"joint":[50],"VAD":[51],"OSD":[53],"(VAD+OSD).":[54],"paper":[56],"investigates":[57],"various":[58],"multi-channel":[59,147],"VAD+OSD":[60,98,129],"front-ends":[61],"that":[62,92],"weight":[63],"combine":[65],"incoming":[66],"channels.":[67],"propose":[69],"three":[70],"algorithms":[71],"based":[72],"on":[73,86,133,192],"Self-Attention":[75],"Channel":[76,127],"Combinator":[77],"(SACC),":[78],"previously":[79],"proposed":[80,175],"in":[81,100,123,159],"literature.":[83],"Experiments":[84],"conducted":[85,191],"AMI":[88],"corpus":[90],"exhibit":[91],"channel":[93],"combination":[94,113],"approaches":[95],"bring":[96],"significant":[97,143],"improvements":[99],"scenario.":[104],"Specifically,":[105],"we":[106],"explore":[107],"use":[109],"of":[110,119,125,168,183,186,199],"learned":[111],"complex":[112],"weights":[114],"demonstrate":[116],"benefits":[118],"such":[120],"an":[121],"approach":[122],"terms":[124],"explainability.":[126],"combination-based":[128],"systems":[130,148],"evaluated":[132],"final":[135],"back-end":[136],"task,":[137],"i.e.":[138],"diarization,":[140],"show":[142],"improvements.":[144],"Finally,":[145],"since":[146],"trained":[150],"given":[151],"fixed":[153],"array":[154,163,194],"configuration,":[155],"they":[156],"may":[157],"fail":[158],"generalizing":[160],"other":[162],"set-ups,":[164],"e.g.":[165],"mismatched":[166,193],"number":[167,185],"microphones.":[169,188],"A":[170],"channel-number":[171],"invariant":[172],"loss":[173],"learn":[177],"unique":[179],"feature":[180],"representation":[181],"regardless":[182],"available":[187],"The":[189],"evaluation":[190],"configurations":[195],"highlights":[196],"robustness":[198],"this":[200],"training":[201],"strategy.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}