{"id":"https://openalex.org/W2407001684","doi":"https://doi.org/10.21437/interspeech.2013-638","title":"Combining deep speaker specific representations with GMM-SVM for speaker verification","display_name":"Combining deep speaker specific representations with GMM-SVM for speaker verification","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2407001684","doi":"https://doi.org/10.21437/interspeech.2013-638","mag":"2407001684"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-638","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5028120017","display_name":"Ryan Price","orcid":"https://orcid.org/0000-0003-0624-6629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryan Price","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055393993","display_name":"Sangeeta Biswas","orcid":"https://orcid.org/0000-0001-6322-8836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sangeeta Biswas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24107681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2788","last_page":"2792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9930999875068665,"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":0.9930999875068665,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9107000231742859,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.8595808744430542},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7693837881088257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7592068910598755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7318302392959595},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6387844085693359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.62030428647995},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6170669794082642},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5812796354293823},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46824896335601807},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4276093542575836}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8595808744430542},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7693837881088257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592068910598755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7318302392959595},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6387844085693359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.62030428647995},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6170669794082642},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5812796354293823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46824896335601807},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4276093542575836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-638","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004068111","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100659865","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH2013","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W66821593","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2144470400","https://openalex.org/W2997340161","https://openalex.org/W2911612049","https://openalex.org/W1964028329"],"abstract_inverted_index":{"This":[0],"study":[1],"combines":[2],"a":[3,13,43,51,61,77,81,94,112],"Gaussian":[4],"mixture":[5],"model":[6],"support":[7],"vector":[8],"machine":[9],"(GMM-SVM)":[10],"system":[11,125],"with":[12],"nonlinear":[14],"feature":[15,142],"transformation,":[16],"discriminatively":[17],"trained":[18,78],"to":[19,76,111],"extract":[20],"speaker":[21,29,57,106,138],"specific":[22],"features":[23,73,92],"from":[24],"MFCCs.":[25],"Separation":[26],"of":[27,63,69,83,101,114],"the":[28,37,64,99,115,132],"information":[30,35,58],"component":[31],"and":[32,80],"non-speaker":[33],"related":[34],"in":[36,93],"speech":[38,70],"signal":[39],"is":[40],"accomplished":[41],"using":[42,67],"regularized":[44],"siamese":[45],"deep":[46],"network":[47],"(RSDN).":[48],"RSDN":[49,79,123],"learns":[50],"hidden":[52,65,84],"representation":[53],"that":[54],"well":[55],"characterizes":[56],"by":[59,108],"training":[60],"subset":[62,82,113],"units":[66],"pairs":[68],"segments.":[71],"MFCC":[72],"are":[74,87],"input":[75,91],"layer":[85],"outputs":[86],"used":[88],"as":[89],"new":[90],"GMM-SVM":[95,124,134,144],"system.":[96,135],"We":[97],"demonstrate":[98],"potential":[100],"this":[102],"approach":[103],"for":[104],"text-independent":[105],"verification":[107],"applying":[109],"it":[110],"NIST":[116],"SRE":[117],"2006":[118],"1conv4w-1conv4w":[119],"task.":[120],"The":[121],"hybrid":[122],"achieves":[126],"about":[127],"5%":[128],"relative":[129],"improvement":[130],"over":[131],"baseline":[133],"Index":[136],"Terms:":[137],"verification,":[139],"neural":[140],"networks,":[141],"extraction,":[143]},"counts_by_year":[],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}