{"id":"https://openalex.org/W1912949653","doi":"https://doi.org/10.21437/interspeech.2012-166","title":"Phone adaptive training for speaker diarization","display_name":"Phone adaptive training for speaker diarization","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W1912949653","doi":"https://doi.org/10.21437/interspeech.2012-166","mag":"1912949653"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-166","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.archives-ouvertes.fr/hal-00733385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010332658","display_name":"Simon Bozonnet","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Bozonnet","raw_affiliation_strings":["Eurecom, Sophia Antipolis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eurecom, Sophia Antipolis","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069973475","display_name":"Ravichander Vipperla","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ravichander Vipperla","raw_affiliation_strings":["Eurecom, Sophia Antipolis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eurecom, Sophia Antipolis","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":["Eurecom, Sophia Antipolis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eurecom, Sophia Antipolis","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1902872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"494","last_page":"497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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":0.994700014591217,"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":0.9252548217773438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007830381393433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7684746980667114},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7540024518966675},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6995521783828735},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5429955720901489},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5216192007064819},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.45290452241897583},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.43534114956855774},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4308335781097412},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06550031900405884}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9252548217773438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007830381393433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7684746980667114},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7540024518966675},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6995521783828735},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5429955720901489},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5216192007064819},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.45290452241897583},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43534114956855774},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4308335781097412},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06550031900405884},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-166","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00733385v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-00733385","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association, September 9-13, Portland, Oregon, USA","raw_type":"\\ninfo:eu-repo/semantics/conferenceObject\\n"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00733385v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-00733385","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association, September 9-13, Portland, Oregon, USA","raw_type":"\\ninfo:eu-repo/semantics/conferenceObject\\n"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1578764783","https://openalex.org/W1599512239","https://openalex.org/W1815845248","https://openalex.org/W1991661457","https://openalex.org/W2038162002","https://openalex.org/W2103592292","https://openalex.org/W2121981798","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W2061937230","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"The":[0],"linguistic":[1],"content":[2],"of":[3,10,70],"a":[4,8,61],"speech":[5,46],"signal":[6],"is":[7,37],"source":[9],"unwanted":[11],"variation":[12],"which":[13,52],"can":[14],"degrade":[15],"speaker":[16,40],"diarization":[17,67],"performance.This":[18],"paper":[19],"presents":[20],"our":[21,71],"latest":[22],"work":[23],"to":[24,31,39,59],"reduce":[25],"its":[26],"impact.The":[27],"new":[28],"approach,":[29],"referred":[30],"as":[32],"Phone":[33],"Adaptive":[34],"Training":[35],"(PAT),":[36],"analogous":[38],"adaptive":[41],"training":[42],"used":[43],"in":[44,65],"automatic":[45],"recognition.We":[47],"report":[48],"an":[49],"oracle":[50],"experiment":[51],"shows":[53],"that":[54],"PAT":[55],"has":[56],"the":[57,66],"potential":[58],"deliver":[60],"33%":[62],"relative":[63],"improvement":[64],"error":[68],"rate":[69],"baseline":[72],"system.Practical":[73],"experiments":[74],"show":[75],"significant":[76],"improvements":[77],"across":[78],"two":[79],"standard,":[80],"independent":[81],"evaluation":[82],"datasets.":[83]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
