{"id":"https://openalex.org/W1831782169","doi":"https://doi.org/10.21437/odyssey.2014-32","title":"Short-Duration Speaker Modelling with Phone Adaptive Training","display_name":"Short-Duration Speaker Modelling with Phone Adaptive Training","publication_year":2014,"publication_date":"2014-06-16","ids":{"openalex":"https://openalex.org/W1831782169","doi":"https://doi.org/10.21437/odyssey.2014-32","mag":"1831782169"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2014-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-32","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027169731","display_name":"Giovanni Soldi","orcid":"https://orcid.org/0000-0003-4426-7850"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Giovanni Soldi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010332658","display_name":"Simon Bozonnet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Bozonnet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009931329","display_name":"Federico Alegre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Federico Alegre","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001027351","display_name":"Christophe Beaugeant","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Beaugeant","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027169731"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8631,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9156474,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"215"},"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":0.9969000220298767,"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":0.9965000152587891,"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/discriminative-model","display_name":"Discriminative model","score":0.8336350917816162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784424364566803},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7300029397010803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7154255509376526},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6566907167434692},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6345466375350952},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6008915901184082},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5954406261444092},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5331565141677856},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41914403438568115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3852919936180115}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8336350917816162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784424364566803},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7300029397010803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7154255509376526},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6566907167434692},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6345466375350952},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6008915901184082},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5954406261444092},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5331565141677856},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41914403438568115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3852919936180115},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2014-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-32","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W17817017","https://openalex.org/W67277430","https://openalex.org/W82466267","https://openalex.org/W1553271421","https://openalex.org/W1599512239","https://openalex.org/W1839748703","https://openalex.org/W1912949653","https://openalex.org/W1998980504","https://openalex.org/W2037740282","https://openalex.org/W2038162002","https://openalex.org/W2049633694","https://openalex.org/W2064364374","https://openalex.org/W2081074144","https://openalex.org/W2103592292","https://openalex.org/W2105667909","https://openalex.org/W2110883784","https://openalex.org/W2121812409","https://openalex.org/W2121981798","https://openalex.org/W2125565816","https://openalex.org/W2143694533","https://openalex.org/W2146871184","https://openalex.org/W2150769028","https://openalex.org/W2168877403","https://openalex.org/W2402704384","https://openalex.org/W2404548572","https://openalex.org/W2407713732","https://openalex.org/W2612380871","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","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"],"abstract_inverted_index":{"This":[0],"paper":[1,75],"presents":[2,76],"a":[3,52,60,107],"new":[4,24,61,77],"approach":[5,25],"to":[6,12,28,79,115],"feature-level":[7],"phone":[8,30],"normalisation":[9],"which":[10,56],"aims":[11],"improve":[13],"speaker":[14,46,72,88,96],"modelling":[15,89],"in":[16,45,68,91],"the":[17,69,85,92,104,116],"case":[18],"of":[19,54,71,87,94,106],"short-duration":[20],"training":[21,32,48],"data.":[22],"The":[23],"is":[26],"referred":[27],"as":[29],"adaptive":[31,47],"(PAT).":[33],"Based":[34],"on":[35],"constrained":[36],"maximum":[37],"likelihood":[38],"linear":[39],"regression":[40],"(cMLLR)":[41],"and":[42,81,90],"previous":[43],"work":[44,78],"(SAT),":[49],"PAT":[50,83,102],"learns":[51],"set":[53],"transforms":[55],"project":[57],"features":[58],"into":[59],"phonenormalised":[62],"but":[63],"speaker-discriminative":[64],"space.":[65],"Originally":[66],"investigated":[67],"context":[70,93],"diarization,":[73],"this":[74],"assess":[80],"optimise":[82],"at":[84],"level":[86],"automatic":[95],"verification":[97],"(ASV).":[98],"Experiments":[99],"show":[100],"that":[101],"improves":[103],"performance":[105],"state-of-the-art":[108],"iVector":[109],"ASV":[110],"system":[111],"by":[112],"50%":[113],"relative":[114],"baseline.":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}