{"id":"https://openalex.org/W2036028057","doi":"https://doi.org/10.1109/icassp.2010.5495632","title":"A comparison of approaches for modeling prosodic features in speaker recognition","display_name":"A comparison of approaches for modeling prosodic features in speaker recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2036028057","doi":"https://doi.org/10.1109/icassp.2010.5495632","mag":"2036028057"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"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":"Luciana Ferrer","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103585404","display_name":"Nicolas Scheffer","orcid":null},"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":"Nicolas Scheffer","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"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":"Elizabeth Shriberg","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4414","last_page":"4417"},"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":0.998199999332428,"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.812006413936615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7393227815628052},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6255142688751221},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6066623330116272},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5941300392150879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5449596047401428},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5437638759613037},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5355600714683533},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5104480981826782},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08116522431373596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812006413936615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7393227815628052},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6255142688751221},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6066623330116272},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5941300392150879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5449596047401428},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5437638759613037},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5355600714683533},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5104480981826782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08116522431373596},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.6365","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.6365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"http://www.speech.sri.com/cgi-bin/run-distill?papers/icassp2010-ferrer.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1563235770","https://openalex.org/W1622483327","https://openalex.org/W1983746412","https://openalex.org/W1989674379","https://openalex.org/W2041823554","https://openalex.org/W2101338313","https://openalex.org/W2107713197","https://openalex.org/W2118039276","https://openalex.org/W2121415728","https://openalex.org/W2121765613","https://openalex.org/W2139048635","https://openalex.org/W2153410846","https://openalex.org/W2161964681","https://openalex.org/W2167022632","https://openalex.org/W2170065313","https://openalex.org/W2257601841","https://openalex.org/W6636526691","https://openalex.org/W6646381949","https://openalex.org/W6692607234"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W4297807400"],"abstract_inverted_index":{"Prosodic":[0],"information":[1],"has":[2,20],"been":[3,21],"successfully":[4],"used":[5],"for":[6,9,85,94,102],"speaker":[7,45],"recognition":[8,33],"more":[10],"than":[11],"a":[12,41,55,97,130],"decade.":[13],"The":[14,35],"best-performing":[15],"prosodic":[16],"system":[17],"to":[18,66,143],"date":[19],"one":[22],"based":[23,61],"on":[24,62],"features":[25,36],"extracted":[26],"over":[27,124],"syllables":[28],"obtained":[29],"automatically":[30],"from":[31],"speech":[32],"output.":[34],"are":[37,47],"then":[38],"transformed":[39],"using":[40,49,71,151],"Fisher":[42],"kernel,":[43],"and":[44],"models":[46],"trained":[48],"support":[50],"vector":[51],"machines":[52],"(SVMs).":[53],"Recently,":[54],"simpler":[56,87],"version":[57],"of":[58,89,99,118,133],"these":[59,95],"features,":[60,96],"pseudo-syllables":[63],"was":[64],"shown":[65],"perform":[67],"well":[68],"when":[69],"modeled":[70],"joint":[72],"factor":[73],"analysis":[74],"(JFA).":[75],"In":[76],"this":[77],"work,":[78],"we":[79,113],"study":[80],"the":[81,86,116,125,136,144],"two":[82,145],"modeling":[83,110],"techniques":[84],"set":[88],"features.":[90],"We":[91],"show":[92,114],"that,":[93],"combination":[98,117],"JFA":[100],"systems":[101],"different":[103],"sequence":[104],"lengths":[105],"greatly":[106],"outperforms":[107],"both":[108,119],"original":[109],"methods.":[111],"Furthermore,":[112],"that":[115],"methods":[120,148],"gives":[121],"significant":[122],"improvements":[123],"best":[126],"single":[127],"system.":[128],"Overall,":[129],"performance":[131],"improvement":[132],"30%":[134],"in":[135],"detection":[137],"cost":[138],"function":[139],"(DCF)":[140],"with":[141],"respect":[142],"previously":[146],"published":[147],"is":[149],"achieved":[150],"very":[152],"simple":[153],"strategies.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}