{"id":"https://openalex.org/W2889492015","doi":"https://doi.org/10.21437/interspeech.2018-1804","title":"Employing Phonetic Information in DNN Speaker Embeddings to Improve Speaker Recognition Performance","display_name":"Employing Phonetic Information in DNN Speaker Embeddings to Improve Speaker Recognition Performance","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889492015","doi":"https://doi.org/10.21437/interspeech.2018-1804","mag":"2889492015"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1804","doi":"https://doi.org/10.21437/interspeech.2018-1804","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1804","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5079425599","display_name":"Md Hafizur Rahman","orcid":"https://orcid.org/0000-0002-1981-6582","observed_orcids":["https://orcid.org/0000-0002-1981-6582"]},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Md Hafizur Rahman","raw_affiliation_strings":[".fookes 4 ,","Speech and Audio Research Laboratory, Queensland University of Technology, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":".fookes 4 ,","institution_ids":[]},{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X","observed_orcids":["https://orcid.org/0000-0003-3848-244X"]},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":[".fookes 4 ,","Speech and Audio Research Laboratory, Queensland University of Technology, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":".fookes 4 ,","institution_ids":[]},{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060382325","display_name":"Mitchell McLaren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":[".fookes 4 ,","Speech and Audio Research Laboratory, Queensland University of Technology, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":".fookes 4 ,","institution_ids":[]},{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324","observed_orcids":["https://orcid.org/0000-0002-8515-6324"]},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":[".fookes 4 ,","Speech and Audio Research Laboratory, Queensland University of Technology, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":".fookes 4 ,","institution_ids":[]},{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001","observed_orcids":["https://orcid.org/0000-0003-4316-9001"]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5308,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.69222725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3593","last_page":"3597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-embedding","display_name":"speaker embedding","score":0.878000020980835},{"id":"https://openalex.org/keywords/text-independent-speaker-recognition","display_name":"text-independent speaker recognition","score":0.7919999957084656},{"id":"https://openalex.org/keywords/phonetic-information","display_name":"phonetic information","score":0.8460000157356262},{"id":"https://openalex.org/keywords/bottleneck-features","display_name":"bottleneck features","score":0.9900000095367432},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.9369999766349792},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.6380000114440918},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.7179999947547913}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.8214621543884277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8110311031341553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831827402114868},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7308164238929749},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4216906726360321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34349334239959717}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1804","doi":"https://doi.org/10.21437/interspeech.2018-1804","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1804","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:119838","doi":null,"is_oa":false,"landing_page_url":"https://eprints.qut.edu.au/119838/1/template.pdf","pdf_url":"https://eprints.qut.edu.au/119838/1/template.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 19th Annual Conference of the International Speech Communication Association (INTERSPEECH 2018)","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W151003953","https://openalex.org/W1524333225","https://openalex.org/W1528954144","https://openalex.org/W1665214252","https://openalex.org/W2046056978","https://openalex.org/W2078169166","https://openalex.org/W2094035326","https://openalex.org/W2096733369","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2175575774","https://openalex.org/W2185814970","https://openalex.org/W2194775991","https://openalex.org/W2290689761","https://openalex.org/W2406312423","https://openalex.org/W2407857848","https://openalex.org/W2515282169","https://openalex.org/W2565624985","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2807305309","https://openalex.org/W2890964092"],"related_works":["https://openalex.org/W2887499727","https://openalex.org/W2039057510","https://openalex.org/W4366147765","https://openalex.org/W4393117624","https://openalex.org/W2964247977","https://openalex.org/W2976255838","https://openalex.org/W2612434969","https://openalex.org/W3196415493","https://openalex.org/W2993724474","https://openalex.org/W2489978256"],"abstract_inverted_index":{"The":[0,19],"recent":[1],"speaker":[2,17,48,61,122,142],"embeddings":[3,98],"framework":[4,20],"has":[5],"been":[6],"shown":[7,135],"to":[8,30,102,136,140],"provide":[9,137],"excellent":[10],"performance":[11],"on":[12,23,47,67],"the":[13,58,81,91,104,125,141],"task":[14,59,82],"of":[15,60,83,93],"text-independent":[16],"recognition.":[18,85],"is":[21,55,117,133],"based":[22,66],"a":[24,77,128],"deep":[25],"neural":[26],"network":[27],"(DNN)":[28],"trained":[29,79],"directly":[31],"discriminate":[32],"between":[33],"speakers":[34],"from":[35,76],"traditional":[36],"acoustic":[37],"features":[38,70],"such":[39],"as":[40],"Mel":[41],"frequency":[42],"cepstral":[43],"coefficients.":[44],"Prior":[45],"studies":[46],"recognition":[49],"have":[50],"found":[51],"that":[52,110],"phonetic":[53,94,112],"information":[54,113],"valuable":[56,119],"in":[57,115],"identification,":[62],"with":[63],"systems":[64],"being":[65],"either":[68],"bottleneck":[69],"(BFs)":[71],"or":[72],"tied-triphone":[73],"state":[74],"posteriors":[75],"DNN":[78,97,121,130],"for":[80,96,120],"speech":[84],"In":[86],"this":[87],"paper,":[88],"we":[89],"analyze":[90],"role":[92],"BFs":[95,105,116,126],"and":[99],"explore":[100],"methods":[101],"enhance":[103],"further.":[106],"Experimental":[107],"results":[108],"show":[109],"exploiting":[111],"encoded":[114],"very":[118],"embeddings.":[123],"Enriching":[124],"using":[127],"cascaded":[129],"multi-task":[131],"architecture":[132],"also":[134],"further":[138],"improvements":[139],"embed-":[143],"ding":[144],"system.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2018-09-07T00:00:00"}