{"id":"https://openalex.org/W2095965719","doi":"https://doi.org/10.1109/icassp.2011.5947368","title":"Recent progress in prosodic speaker verification","display_name":"Recent progress in prosodic speaker verification","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2095965719","doi":"https://doi.org/10.1109/icassp.2011.5947368","mag":"2095965719"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5060019900","display_name":"Marcel Kockmann","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Marcel Kockmann","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic","Brno University of Technology, Speech@FIT, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","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/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic","Brno University of Technology, Speech@FIT, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic","Brno University of Technology, Speech@FIT, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4556","last_page":"4559"},"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":0.996399998664856,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9911999702453613,"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/nist","display_name":"NIST","score":0.9340755939483643},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7878724336624146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7263293266296387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7262405753135681},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.63034588098526},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5142626166343689},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49877238273620605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4942760467529297},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4745921790599823},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.461925208568573},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45483914017677307}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.9340755939483643},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7878724336624146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263293266296387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7262405753135681},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.63034588098526},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5142626166343689},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49877238273620605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4942760467529297},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4745921790599823},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.461925208568573},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45483914017677307},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.5365","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.5365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/icassp2011-sid-prosody.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W17749540","https://openalex.org/W153567543","https://openalex.org/W1622483327","https://openalex.org/W1983746412","https://openalex.org/W1989674379","https://openalex.org/W2036028057","https://openalex.org/W2060378667","https://openalex.org/W2121812409","https://openalex.org/W2123768812","https://openalex.org/W2130520294","https://openalex.org/W2136879537","https://openalex.org/W2144158639","https://openalex.org/W2153410846","https://openalex.org/W2406312423","https://openalex.org/W6600721324","https://openalex.org/W6606132431","https://openalex.org/W6636526691","https://openalex.org/W6680375658","https://openalex.org/W6681196357","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835"],"abstract_inverted_index":{"We":[0,78],"describe":[1],"recent":[2],"progress":[3],"in":[4,123],"the":[5,59,96,124],"field":[6],"of":[7,61,110],"prosodic":[8,24,104],"modeling":[9,22],"for":[10,21,32,43,67,102,106],"speaker":[11,107],"verification.":[12],"In":[13,47],"a":[14,19,28,87,103,114],"previous":[15],"paper,":[16,49],"we":[17,50],"proposed":[18],"technique":[20],"syllable-based":[23],"features":[25],"that":[26,52],"uses":[27],"multinomial":[29],"subspace":[30],"model":[31],"feature":[33],"extraction":[34],"and":[35],"within-class":[36],"covariance":[37],"normalization":[38],"or":[39],"linear":[40,63],"discriminant":[41,64],"analysis":[42,65],"session":[44,68],"variability":[45,69],"compensation.":[46,70],"this":[48,94,111],"show":[51],"performance":[53],"can":[54],"be":[55],"significantly":[56],"improved":[57],"with":[58,113],"use":[60],"probabilistic":[62],"(PLDA)":[66],"This":[71],"system":[72,105,112,118],"does":[73],"not":[74],"require":[75],"score":[76],"normalization.":[77],"report":[79],"an":[80],"equal":[81],"error":[82],"rate":[83],"below":[84],"7%":[85],"on":[86],"NIST":[88],"2008":[89],"task.":[90],"To":[91],"our":[92],"knowledge,":[93],"is":[95],"best":[97],"reported":[98],"result":[99],"to":[100],"date":[101],"recognition.":[108],"Fusion":[109],"state-of-the-art":[115],"acoustic":[116],"baseline":[117],"yields":[119],"10%":[120],"relative":[121],"improvement":[122],"new":[125],"detection":[126],"cost":[127],"function":[128],"(DCF)":[129],"as":[130],"defined":[131],"by":[132],"NIST.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
