{"id":"https://openalex.org/W2104835909","doi":"https://doi.org/10.21437/interspeech.2006-366","title":"The segmentation of multi-channel meeting recordings for automatic speech recognition","display_name":"The segmentation of multi-channel meeting recordings for automatic speech recognition","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W2104835909","doi":"https://doi.org/10.21437/interspeech.2006-366","mag":"2104835909"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-366","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/index.php/publications/showcite/dines:rr06-22","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Dines","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106182403","display_name":"Jithendra Vepa","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jithendra Vepa","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["University of  Sheffield"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of  Sheffield","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5791,"has_fulltext":true,"cited_by_count":65,"citation_normalized_percentile":{"value":0.98426573,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"paper 1548","last_page":"Tue3A1O.4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9987999796867371,"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":0.8159208297729492},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.767263650894165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7589938044548035},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7307413816452026},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6778308749198914},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6315723061561584},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.580348551273346},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5057501792907715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46914568543434143},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4257012903690338},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42258119583129883},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4179172217845917},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41642487049102783},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3380935788154602},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08011460304260254},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07326468825340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159208297729492},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.767263650894165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7589938044548035},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7307413816452026},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6778308749198914},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6315723061561584},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.580348551273346},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5057501792907715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46914568543434143},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4257012903690338},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42258119583129883},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4179172217845917},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41642487049102783},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3380935788154602},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08011460304260254},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07326468825340271},{"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/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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2006-366","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:145967","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/dines:rr06-22","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/dines:rr06-22","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},{"id":"pmh:oai:infoscience.tind.io:85992","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/85992","pdf_url":"https://infoscience.epfl.ch/record/85992/files/dines-idiap-rr-06-22.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.3334","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.3334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/papers/2006/dines-interspeech-icslp-2006.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.3984","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.3984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/reports/2006/dines-idiap-rr-06-22.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:145967","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145967","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:145967","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/dines:rr06-22","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/dines:rr06-22","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320331353","display_name":"National Center of Competence in Research Chemical Biology","ror":"https://ror.org/033f9yy33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2104835909.pdf","grobid_xml":"https://content.openalex.org/works/W2104835909.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W76901566","https://openalex.org/W158442874","https://openalex.org/W202968570","https://openalex.org/W1509663858","https://openalex.org/W1534536260","https://openalex.org/W1569447338","https://openalex.org/W1591607137","https://openalex.org/W1946893126","https://openalex.org/W2098441927","https://openalex.org/W2109426048","https://openalex.org/W2161167754","https://openalex.org/W2742679682","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"One":[0,48],"major":[1,51],"research":[2,34],"challenge":[3],"in":[4,53],"the":[5,8,15,32,37,44,50,66,73,88,121,129,158],"domain":[6],"of":[7,10,18,49,75,91,120,128,135,153,157],"analysis":[9,127],"meeting":[11,97,113],"room":[12,114],"data":[13,62],"is":[14,20,63],"automatic":[16,56,89,100],"transcription":[17,40],"what":[19],"spoken":[21],"during":[22],"meetings,":[23],"a":[24,85,125,133,154],"task":[25],"which":[26,70],"has":[27,71],"gained":[28],"considerable":[29],"attention":[30],"within":[31,149],"ASR":[33,143],"community":[35],"through":[36],"NIST":[38],"rich":[39],"evaluations":[41],"conducted":[42],"over":[43],"last":[45],"three":[46],"years.":[47],"difficulties":[52],"carrying":[54],"out":[55],"speech":[57,101],"recognition":[58],"(ASR)":[59],"on":[60,106,145],"this":[61,81],"dealing":[64],"with":[65,138],"challenging":[67],"recording":[68],"environment,":[69],"instigated":[72],"development":[74],"novel":[76],"audio":[77],"pre-processing":[78],"approaches.":[79],"In":[80],"paper":[82],"we":[83],"present":[84],"system":[86,104,136,141],"for":[87,99,132],"segmentation":[90,130,156],"multiple-channel":[92],"individual":[93],"headset":[94],"microphone":[95],"(IHM)":[96],"recordings":[98],"recognition.":[102],"The":[103],"relies":[105],"an":[107],"MLP":[108],"classifier":[109],"trained":[110],"from":[111],"several":[112],"corpora":[115],"to":[116],"identify":[117],"speech/non-speech":[118],"segments":[119,148],"recordings.":[122],"We":[123],"give":[124],"detailed":[126],"performance":[131,144],"number":[134],"configurations,":[137],"our":[139],"best":[140],"achieving":[142],"automatically":[146],"generated":[147],"1.3\\%":[150],"(3.7\\%":[151],"relative)":[152],"manual":[155],"data.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}
