{"id":"https://openalex.org/W2173092938","doi":"https://doi.org/10.21437/interspeech.2015-84","title":"Speaker recognition by means of acoustic and phonetically informed GMMs","display_name":"Speaker recognition by means of acoustic and phonetically informed GMMs","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2173092938","doi":"https://doi.org/10.21437/interspeech.2015-84","mag":"2173092938"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-84","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-84","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","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/A5015516603","display_name":"Sandro Cumani","orcid":"https://orcid.org/0000-0001-6036-0065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandro Cumani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023812879","display_name":"Pietro Laface","orcid":"https://orcid.org/0000-0003-2841-7695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pietro Laface","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015463755","display_name":"Farzana Kulsoom","orcid":"https://orcid.org/0000-0002-0382-5724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farzana Kulsoom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4691,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91089777,"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":"200","last_page":"204"},"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":0.9986000061035156,"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":0.9958999752998352,"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/speech-recognition","display_name":"Speech recognition","score":0.7188824415206909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6712134480476379},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5867957472801208},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42384713888168335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3977108597755432},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.325165331363678}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7188824415206909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712134480476379},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5867957472801208},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42384713888168335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977108597755432},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.325165331363678}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-84","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-84","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:porto.polito.it:2612954","is_oa":false,"landing_page_url":"http://porto.polito.it/2612954/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402038","display_name":"PORTO Publications Open Repository TOrino (Politecnico di Torino)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177477856","host_organization_name":"Politecnico di Torino","host_organization_lineage":["https://openalex.org/I177477856"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W49975404","https://openalex.org/W176831429","https://openalex.org/W330298975","https://openalex.org/W651157033","https://openalex.org/W1481676178","https://openalex.org/W1521002338","https://openalex.org/W1540327379","https://openalex.org/W2039057510","https://openalex.org/W2184045248","https://openalex.org/W2399828378"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2033914206","https://openalex.org/W1197719229","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1516392727"],"abstract_inverted_index":{"In":[0],"this":[1,51,95],"work":[2,52,96],"we":[3],"assess":[4],"the":[5,20,23,26,32,35,45,57,60,65,71,74,80,83,98,107,116,119,133,145,165,168,176],"recently":[6],"proposed":[7],"hybrid":[8],"Deep":[9],"Neural":[10],"Network/Gaussian":[11],"Mixture":[12],"Model":[13],"(DNN/GMM)":[14],"approach":[15],"for":[16,94,106,150],"speaker":[17,100],"recognition":[18,101],"considering":[19],"effects":[21],"of":[22,25,31,34,50,59,73,82,181],"granularity":[24],"phonetic":[27,46,61,120,177],"DNN":[28,66,134,161],"model,":[29],"and":[30,118,178],"precision":[33,180],"corresponding":[36],"GMM":[37],"models,":[38],"which":[39],"will":[40],"be":[41],"referred":[42],"to":[43,54,70,86,144],"as":[44],"GMMs.":[47],"The":[48,92],"aim":[49],"is":[53,135,148,163],"better":[55],"understand":[56],"contributions":[58],"information":[62],"provided":[63],"by":[64,104],"model":[67],"with":[68],"respect":[69],"accuracy":[72],"acous":[75],"tic":[76],"GMMs":[77,121],"in":[78,140],"fitting":[79],"distribution":[81],"features":[84],"associated":[85],"a":[87,157,182],"given":[88],"context-dependent":[89],"phone":[90],"state.":[91],"testbed":[93],"was":[97],"text-independent":[99],"task":[102],"defined":[103],"NIST":[105],"2012":[108],"Speaker":[109],"Recognition":[110],"Evaluation.":[111],"Our":[112],"experiment":[113],"confirms":[114],"that":[115,147,155],"acoustic":[117,179],"are":[122],"complementary.":[123],"Thus,":[124],"their":[125],"score":[126],"combination":[127],"yields":[128],"very":[129],"good":[130],"results":[131],"if":[132],"trained":[136],"on":[137],"data":[138],"collected":[139],"an":[141],"environment":[142],"similar":[143],"one":[146],"used":[149],"testing.":[151],"We":[152],"show,":[153],"however,":[154],"using":[156],"single":[158,170],"Gaussian":[159],"per":[160],"state":[162],"not":[164],"best":[166,169],"choice:":[167],"system":[171,184],"has":[172],"been":[173],"obtained":[174],"balancing":[175],"DNN/GMM":[183]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}