{"id":"https://openalex.org/W1521002338","doi":"https://doi.org/10.21437/interspeech.2005-648","title":"Gaussian mixture modelling of broad phonetic and syllabic events for text-independent speaker verification","display_name":"Gaussian mixture modelling of broad phonetic and syllabic events for text-independent speaker verification","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W1521002338","doi":"https://doi.org/10.21437/interspeech.2005-648","mag":"1521002338"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-648","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/15491/1/broad_phone_official.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103337639","display_name":"Brendan Baker","orcid":null},"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":true,"raw_author_name":"Brendan Baker","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, GPO Box 2434, Brisbane, AUSTRALIA, 4001"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, GPO Box 2434, Brisbane, AUSTRALIA, 4001","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109211991","display_name":"Robbie Vogt","orcid":null},"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":"Robbie Vogt","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, GPO Box 2434, Brisbane, AUSTRALIA, 4001"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, GPO Box 2434, Brisbane, AUSTRALIA, 4001","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"},"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":"Sridha Sridharan","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, GPO Box 2434, Brisbane, AUSTRALIA, 4001"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, GPO Box 2434, Brisbane, AUSTRALIA, 4001","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103337639"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":3.1969,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91795557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2429","last_page":"2432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976999759674072,"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":0.9821000099182129,"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/syllabic-verse","display_name":"Syllabic verse","score":0.9007229804992676},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.813566267490387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7913926839828491},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6790263652801514},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6752699613571167},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6380969285964966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5730891227722168},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5223135352134705},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5131505131721497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5121796131134033},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5111568570137024},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.49230968952178955},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47323358058929443},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4588296115398407},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4533320367336273},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4527963101863861},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3557528257369995},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12462234497070312}],"concepts":[{"id":"https://openalex.org/C194051139","wikidata":"https://www.wikidata.org/wiki/Q2629608","display_name":"Syllabic verse","level":2,"score":0.9007229804992676},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.813566267490387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913926839828491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6790263652801514},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6752699613571167},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6380969285964966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5730891227722168},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5223135352134705},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5131505131721497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5121796131134033},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5111568570137024},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.49230968952178955},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47323358058929443},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4588296115398407},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4533320367336273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4527963101863861},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3557528257369995},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12462234497070312},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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.2005-648","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:15491","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/15491/1/broad_phone_official.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,"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":"Eurospeech/Interspeech: Proceedings of the 9th European Conference on Speech Communication and Technology 2005","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:15491","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/15491/1/broad_phone_official.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,"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":"Eurospeech/Interspeech: Proceedings of the 9th European Conference on Speech Communication and Technology 2005","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1521002338.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W97107628","https://openalex.org/W2114851258","https://openalex.org/W2187693774","https://openalex.org/W2397634864","https://openalex.org/W2403736647","https://openalex.org/W2408222853","https://openalex.org/W2595741664","https://openalex.org/W3145058808"],"related_works":["https://openalex.org/W2254467971","https://openalex.org/W3122402893","https://openalex.org/W2035036138","https://openalex.org/W2364360542","https://openalex.org/W2385848593","https://openalex.org/W57477431","https://openalex.org/W2365880448","https://openalex.org/W206077614","https://openalex.org/W2012908814","https://openalex.org/W1990397005"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"the":[3,47,54,79,92,107],"usefulness":[4],"of":[5,46,78,109,118],"a":[6,23,39,69],"multilingual":[7],"broad":[8],"syllable-based":[9,62],"framework":[10,95,113],"for":[11,26,43,53,115],"text-independent":[12],"speaker":[13,57,103],"verification.":[14],"Syllabic":[15],"segmentation":[16],"is":[17,65,82],"used":[18],"in":[19,89],"order":[20],"to":[21,67,85,101],"obtain":[22],"convenient":[24],"unit":[25],"constrained":[27],"and":[28,124],"more":[29],"detailed":[30],"model":[31],"generation.":[32],"Gaussian":[33],"mixture":[34],"models":[35],"are":[36,51],"chosen":[37],"as":[38,98],"suitable":[40],"modelling":[41,63,120],"paradigm":[42],"initial":[44],"testing":[45,117],"framework.":[48],"Promising":[49],"results":[50],"presented":[52],"NIST":[55],"2003":[56],"recognition":[58],"evaluation":[59],"corpus.":[60],"The":[61,112],"technique":[64],"shown":[66,84],"outperform":[68],"state-of-the-art":[70],"baseline":[71],"GMM":[72],"system.":[73],"A":[74],"simple":[75],"selective":[76],"reduction":[77],"syllable":[80,93],"set":[81],"also":[83],"give":[86],"further":[87],"improvement":[88],"performance.":[90],"Overall,":[91],"based":[94],"presents":[96],"itself":[97],"valid":[99],"alternative":[100,119],"text-constrained":[102],"verification":[104],"systems,":[105],"with":[106],"advantage":[108],"being":[110],"multilingual.":[111],"allows":[114],"future":[116],"paradigms,":[121],"feature":[122],"sets":[123],"qualitative":[125],"analysis.":[126]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}