{"id":"https://openalex.org/W4385822248","doi":"https://doi.org/10.21437/interspeech.2023-684","title":"Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features","display_name":"Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Features","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822248","doi":"https://doi.org/10.21437/interspeech.2023-684"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-684","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/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":"funder","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"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]},{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Th\u00e9o Mariotte","raw_affiliation_strings":["LAUM UMR CNRS 6613 IAGS, Le Mans Universit\u00e9, France","LIUM, Le Mans Universit\u00e9, France"],"affiliations":[{"raw_affiliation_string":"LAUM UMR CNRS 6613 IAGS, Le Mans Universit\u00e9, France","institution_ids":["https://openalex.org/I4210132387","https://openalex.org/I1294671590","https://openalex.org/I4210108471"]},{"raw_affiliation_string":"LIUM, Le Mans Universit\u00e9, France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002979461","display_name":"Anthony Larcher","orcid":"https://orcid.org/0000-0003-4398-0224"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]},{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anthony Larcher","raw_affiliation_strings":["LIUM, Le Mans Universit\u00e9, France"],"affiliations":[{"raw_affiliation_string":"LIUM, Le Mans Universit\u00e9, France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032144114","display_name":"Silvio Montr\u00e9sor","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","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":["LAUM UMR CNRS 6613 IAGS, Le Mans Universit\u00e9, France"],"affiliations":[{"raw_affiliation_string":"LAUM UMR CNRS 6613 IAGS, Le Mans Universit\u00e9, France","institution_ids":["https://openalex.org/I4210132387","https://openalex.org/I1294671590","https://openalex.org/I4210108471"]}]},{"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/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]},{"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"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Hugh Thomas","raw_affiliation_strings":["LAUM UMR CNRS 6613 IAGS, Le Mans Universit\u00e9, France"],"affiliations":[{"raw_affiliation_string":"LAUM UMR CNRS 6613 IAGS, Le Mans Universit\u00e9, France","institution_ids":["https://openalex.org/I4210132387","https://openalex.org/I1294671590","https://openalex.org/I4210108471"]}]}],"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/I234216984","https://openalex.org/I4210108471","https://openalex.org/I4210132387"],"apc_list":null,"apc_paid":null,"fwci":0.4066,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56462415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9839000105857849,"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":0.9839000105857849,"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":0.972100019454956,"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":0.9470999836921692,"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/computer-science","display_name":"Computer science","score":0.7428908348083496},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.671932578086853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6672272682189941},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6576839685440063},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5534070134162903},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4963842034339905},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4940543472766876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42358309030532837},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12722355127334595},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09196943044662476},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06609612703323364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428908348083496},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.671932578086853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6672272682189941},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6576839685440063},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5534070134162903},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4963842034339905},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4940543472766876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42358309030532837},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12722355127334595},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09196943044662476},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06609612703323364},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-684","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W21371201","https://openalex.org/W962432006","https://openalex.org/W1484181928","https://openalex.org/W1598201010","https://openalex.org/W2009876684","https://openalex.org/W2081074144","https://openalex.org/W2114970513","https://openalex.org/W2125336414","https://openalex.org/W2129120544","https://openalex.org/W2403186097","https://openalex.org/W2406262283","https://openalex.org/W2406713305","https://openalex.org/W2514127661","https://openalex.org/W2673722796","https://openalex.org/W2746241180","https://openalex.org/W2772736377","https://openalex.org/W2918296821","https://openalex.org/W2947942791","https://openalex.org/W2963702081","https://openalex.org/W2981728176","https://openalex.org/W2989863749","https://openalex.org/W3011644191","https://openalex.org/W3015780472","https://openalex.org/W3015783745","https://openalex.org/W3016257794","https://openalex.org/W3113518618","https://openalex.org/W3157070662","https://openalex.org/W3178462146","https://openalex.org/W3203236698","https://openalex.org/W3212886388","https://openalex.org/W4283836186","https://openalex.org/W4285618512","https://openalex.org/W4287235989"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"Speaker":[0,53],"diarization":[1],"is":[2],"the":[3,40,57,63,83,103,112],"task":[4],"of":[5,75,119],"answering":[6],"Who":[7],"spoke":[8],"and":[9,24,52,96],"when?":[10],"in":[11,39,82,117],"an":[12],"audio":[13,94],"stream.Pipeline":[14],"systems":[15],"rely":[16],"on":[17,79,102],"speech":[18,42,66],"segmentation":[19,37,113],"to":[20,34],"extract":[21],"speakers'":[22],"segments":[23],"achieve":[25],"robust":[26,116],"speaker":[27],"diarization.This":[28],"paper":[29],"proposes":[30],"a":[31,59,72],"common":[32],"framework":[33],"solve":[35],"three":[36],"tasks":[38],"distant":[41,65],"scenario:":[43],"Voice":[44],"Activity":[45],"Detection":[46,50,55],"(VAD),":[47],"Overlapped":[48],"Speech":[49],"(OSD),":[51],"Change":[54],"(SCD).In":[56],"literature,":[58],"few":[60],"studies":[61],"investigate":[62],"multi-microphone":[64,93],"scenario.In":[67],"this":[68],"work,":[69],"we":[70],"propose":[71],"new":[73],"set":[74],"spatial":[76,88],"features":[77,89],"based":[78],"direction-of-arrival":[80],"estimations":[81],"circular":[84],"harmonic":[85],"domain":[86],"(CH-DOA).These":[87],"are":[90],"extracted":[91],"from":[92],"data":[95],"combined":[97],"with":[98],"standard":[99],"acoustic":[100],"features.Experiments":[101],"AMI":[104],"meeting":[105],"corpus":[106],"show":[107],"that":[108],"CH-DOA":[109],"can":[110],"improve":[111],"while":[114],"being":[115],"case":[118],"deactivated":[120],"microphones.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}