{"id":"https://openalex.org/W814827736","doi":"https://doi.org/10.21437/odyssey.2014-30","title":"Modeling Overlapping Speech using Vector Taylor Series","display_name":"Modeling Overlapping Speech using Vector Taylor Series","publication_year":2014,"publication_date":"2014-06-16","ids":{"openalex":"https://openalex.org/W814827736","doi":"https://doi.org/10.21437/odyssey.2014-30","mag":"814827736"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2014-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/199811","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063425263","display_name":"Pranay Dighe","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pranay Dighe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027284390","display_name":"Marc Ferr\u00e0s","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Ferras","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063425263"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4229,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72536652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8232547044754028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666720151901245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7233636379241943},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5451116561889648},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5419309139251709},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4413143992424011},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.43393343687057495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3981861174106598},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07115861773490906}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8232547044754028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666720151901245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7233636379241943},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5451116561889648},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5419309139251709},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4413143992424011},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.43393343687057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3981861174106598},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07115861773490906},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/odyssey.2014-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.6901","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.6901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.uef.fi/odyssey2014/program/pdfs/9.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:199811","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/199811","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":"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":"Text"},{"id":"pmh:oai:infoscience.tind.io:199811","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/104508","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":"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":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:199811","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/199811","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":"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":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W80245499","https://openalex.org/W1558276682","https://openalex.org/W1665196592","https://openalex.org/W1865095259","https://openalex.org/W1910232678","https://openalex.org/W2000949213","https://openalex.org/W2041823554","https://openalex.org/W2079362249","https://openalex.org/W2090716422","https://openalex.org/W2098726438","https://openalex.org/W2101702585","https://openalex.org/W2136745572","https://openalex.org/W2148613904","https://openalex.org/W2155445312","https://openalex.org/W2157850507","https://openalex.org/W2169264834","https://openalex.org/W2402428045","https://openalex.org/W3143522270"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Current":[0],"speaker":[1,52,78],"diarization":[2,59],"systems":[3],"typically":[4],"fail":[5],"to":[6,14,45,66,71,87],"success-fully":[7],"assign":[8],"multiple":[9,68],"speakers":[10,98],"speaking":[11],"simultaneously.":[12],"Ac-cording":[13],"previous":[15],"studies,":[16],"overlapping":[17,47,92],"errors":[18,27],"account":[19,72],"for":[20,73],"a":[21,37,82],"large":[22],"proportion":[23],"of":[24,76,104],"the":[25,58,63,74,97,102,105,114,119],"total":[26],"in":[28],"multi-party":[29],"speech":[30,48,93],"di-arization.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"propose":[36,81],"new":[38],"approach":[39,106,116],"using":[40,84],"Vec-tor":[41],"Taylor":[42],"Series":[43],"(VTS)":[44],"obtain":[46],"models":[49,53],"assuming":[50],"individual":[51],"are":[54],"available,":[55],"e.g.":[56],"from":[57],"output.":[60],"We":[61,80,100],"extend":[62],"VTS":[64,86],"framework":[65],"use":[67],"acoustic":[69],"classes":[70],"non-stationarity":[75],"corrupting":[77],"speech.":[79],"system":[83],"multi-class":[85,115],"detect":[88],"single-speaker":[89],"and":[90],"two-speaker":[91],"as":[94,96],"well":[95],"involved.":[99],"show":[101],"effectivity":[103],"on":[107],"distant":[108],"microphone":[109],"meeting":[110],"data,":[111],"especially":[112],"with":[113],"performing":[117],"at":[118],"state-of-the-art.":[120],"1.":[121]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
