{"id":"https://openalex.org/W2153144850","doi":"https://doi.org/10.1109/icassp.2009.4960641","title":"On separating glottal source and vocal tract information in telephony speaker verification","display_name":"On separating glottal source and vocal tract information in telephony speaker verification","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2153144850","doi":"https://doi.org/10.1109/icassp.2009.4960641","mag":"2153144850"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960641","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/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["Department of Computer Science and Statistics, University of Joensuu, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Statistics, University of Joensuu, Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Helsinki University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Helsinki University of Technology, Finland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043168931"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5163,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94791047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4545","last_page":"4548"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.9796000123023987,"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/vocal-tract","display_name":"Vocal tract","score":0.9457961320877075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7944507002830505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.723548948764801},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6427546739578247},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.6098418831825256},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5770071148872375},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5397435426712036},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.49756506085395813},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.44658803939819336},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4225926101207733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3026764392852783},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.16603660583496094},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1297002136707306}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.9457961320877075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7944507002830505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723548948764801},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6427546739578247},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.6098418831825256},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5770071148872375},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5397435426712036},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.49756506085395813},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.44658803939819336},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4225926101207733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3026764392852783},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.16603660583496094},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1297002136707306}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960641","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:10.1.1.144.4073","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.4073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/iaif-speaker-recognition.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W8440297","https://openalex.org/W36105149","https://openalex.org/W955355846","https://openalex.org/W1557133539","https://openalex.org/W1969107787","https://openalex.org/W1986060991","https://openalex.org/W2041823554","https://openalex.org/W2103075368","https://openalex.org/W2112164460","https://openalex.org/W2118209063","https://openalex.org/W2118436560","https://openalex.org/W2131221986","https://openalex.org/W2151225171","https://openalex.org/W2398498689","https://openalex.org/W6600365573","https://openalex.org/W6712629645"],"related_works":["https://openalex.org/W1482212662","https://openalex.org/W2100012411","https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W1997579527","https://openalex.org/W2102353451","https://openalex.org/W3044927199","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097"],"abstract_inverted_index":{"The":[0],"popular":[1],"mel-frequency":[2,88],"cepstral":[3],"coefficients":[4],"(MFCCs)":[5],"capture":[6],"a":[7],"mixture":[8],"of":[9,52,79,90],"speaker-related,":[10],"phonemic":[11],"and":[12,55],"channel":[13],"information.":[14],"Speaker-related":[15],"information":[16,118],"could":[17],"be":[18,120],"further":[19],"broken":[20],"down":[21],"according":[22],"to":[23,65],"articulatory":[24],"criteria.":[25],"How":[26],"these":[27],"underlying":[28],"components":[29],"are":[30],"exactly":[31],"mixed":[32],"in":[33,43],"the":[34,50,74,80,87,91,102,105],"features":[35],"is":[36,94],"not":[37,95],"well":[38],"understood.":[39],"To":[40],"this":[41,44],"end,":[42],"paper":[45],"we":[46],"aim":[47],"at":[48],"separating":[49],"spectra":[51],"glottal":[53,59],"source":[54,93],"vocal":[56,106,116],"tract":[57,107,117],"using":[58],"inverse":[60],"filtering,":[61],"with":[62,109],"an":[63],"application":[64],"speaker":[66],"recognition":[67],"over":[68],"telephone":[69],"lines.":[70],"Our":[71],"experiments":[72],"on":[73],"10":[75],"sec-10":[76],"sec":[77],"condition":[78],"NIST":[81],"2006":[82],"SRE":[83],"corpus":[84],"suggest":[85],"that":[86,115],"cepstrum":[89],"voice":[92],"too":[96],"useful":[97],"for":[98],"recognizing":[99],"speakers.":[100],"On":[101],"contrary,":[103],"fusing":[104],"spectrum":[108],"conventional":[110],"MFCCs":[111],"improves":[112],"accuracy,":[113],"suggesting":[114],"should":[119],"enhanced.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}