{"id":"https://openalex.org/W2136105097","doi":"https://doi.org/10.1109/icassp.2009.4960640","title":"Modeling instantaneous intonation for speaker identification using the fundamental frequency variation spectrum","display_name":"Modeling instantaneous intonation for speaker identification using the fundamental frequency variation spectrum","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2136105097","doi":"https://doi.org/10.1109/icassp.2009.4960640","mag":"2136105097"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5030859194","display_name":"Kornel Laskowski","orcid":"https://orcid.org/0009-0008-8060-6913"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kornel Laskowski","raw_affiliation_strings":["Cognitive Systems Laboratory, Universit\u00e4t Karlsruhe, Karlsruhe, Germany","InterACT, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Cognitive Systems Laboratory, Universit\u00e4t Karlsruhe, Karlsruhe, Germany","institution_ids":[]},{"raw_affiliation_string":"InterACT, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101665677","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0003-4163-6067"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["InterACT, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"InterACT, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030859194"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.6041,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93287773,"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":"4541","last_page":"4544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.9944999814033508,"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/speech-recognition","display_name":"Speech recognition","score":0.6936375498771667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899139285087585},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6558594703674316},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.6039457321166992},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5495636463165283},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5432090163230896},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5278187394142151},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.47056031227111816},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.46592044830322266},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4580075442790985},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44119566679000854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42404884099960327},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42091572284698486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41317421197891235},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.20956951379776},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1926060914993286}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6936375498771667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899139285087585},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6558594703674316},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.6039457321166992},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5495636463165283},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5432090163230896},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5278187394142151},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.47056031227111816},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.46592044830322266},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4580075442790985},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44119566679000854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42404884099960327},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42091572284698486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41317421197891235},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.20956951379776},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1926060914993286},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.1743","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.1743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~kornel/pubs/0004541.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1563235770","https://openalex.org/W1751091532","https://openalex.org/W1995966271","https://openalex.org/W2004245236","https://openalex.org/W2041823554","https://openalex.org/W2103069945","https://openalex.org/W2107012119","https://openalex.org/W2114851258","https://openalex.org/W2135374333","https://openalex.org/W2162273278","https://openalex.org/W2165880886","https://openalex.org/W6633897942","https://openalex.org/W6675747831","https://openalex.org/W6677061356","https://openalex.org/W6679896430"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2111580133","https://openalex.org/W2101922478"],"abstract_inverted_index":{"In":[0,116],"recent":[1],"years,":[2],"the":[3,57],"field":[4],"of":[5,15,23,45,56,73,107,132],"automatic":[6],"speaker":[7],"identification":[8],"has":[9],"begun":[10],"to":[11,20],"exploit":[12],"high-level":[13],"sources":[14,27],"speaker-discriminative":[16],"information,":[17],"in":[18,60,82,129],"addition":[19],"traditional":[21],"models":[22],"spectral":[24],"shape.":[25],"These":[26],"include":[28],"pronunciation":[29],"models,":[30],"prosodic":[31],"dynamics,":[32],"pitch,":[33],"pause,":[34],"and":[35,40,77,103,109,134,138],"duration":[36],"features,":[37],"phone":[38],"streams,":[39],"conversational":[41],"interaction.":[42],"As":[43],"part":[44],"this":[46],"broader":[47],"thrust,":[48],"we":[49],"explore":[50],"a":[51,83],"new":[52],"frame-level":[53],"vector":[54],"representation":[55],"instantaneous":[58],"change":[59],"fundamental":[61,65],"frequency,":[62],"known":[63],"as":[64],"frequency":[66],"variation":[67],"(FFV).":[68],"The":[69],"FFV":[70,94,108],"spectrum":[71],"consists":[72],"7":[74],"continuous":[75],"coefficients,":[76],"can":[78],"be":[79],"directly":[80],"modeled":[81],"standard":[84],"Gaussian":[85],"mixture":[86],"model":[87],"(GMM)":[88],"framework.":[89],"Our":[90],"experiments":[91],"indicate":[92],"that":[93,104],"features":[95,111,114],"contain":[96],"useful":[97],"information":[98],"for":[99,136],"discriminating":[100],"among":[101],"speakers,":[102,140],"model-space":[105],"combination":[106],"cepstral":[110,113],"outperforms":[112],"alone.":[115],"particular,":[117],"our":[118],"results":[119],"on":[120],"16kHz":[121],"Wall":[122],"Street":[123],"Journal":[124],"data":[125],"show":[126],"relative":[127],"reductions":[128],"error":[130],"rate":[131],"54%":[133],"40%":[135],"female":[137],"male":[139],"respectively.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}