{"id":"https://openalex.org/W2138847091","doi":"https://doi.org/10.1109/icassp.2004.1326008","title":"A pitch synchronous feature extraction method for speaker recognition","display_name":"A pitch synchronous feature extraction method for speaker recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2138847091","doi":"https://doi.org/10.1109/icassp.2004.1326008","mag":"2138847091"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5011157348","display_name":"Sunah Kim","orcid":"https://orcid.org/0000-0001-5922-6598"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"S. Kim","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011869976","display_name":"Thomas Eriksson","orcid":"https://orcid.org/0000-0002-2087-7227"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"T. Eriksson","raw_affiliation_strings":["Department of Signals and Systems, Chalmers University of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signals and Systems, Chalmers University of Technology, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101203935","display_name":"Hong-Goo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108514747","display_name":"Dae Hee Youn","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dae Hee Youn","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7001,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9339808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"405"},"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":0.9972000122070312,"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":0.9894999861717224,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8805865049362183},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7625728845596313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7586132884025574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6897698640823364},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6417383551597595},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.631458044052124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6159712076187134},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.551782488822937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5321333408355713},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5168014764785767},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5093611478805542},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45634493231773376},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45629405975341797},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41968071460723877},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41617876291275024}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8805865049362183},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7625728845596313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586132884025574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6897698640823364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6417383551597595},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.631458044052124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6159712076187134},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.551782488822937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321333408355713},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5168014764785767},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5093611478805542},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45634493231773376},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45629405975341797},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41968071460723877},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41617876291275024},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2004.1326008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.lib.chalmers.se:15277","is_oa":false,"landing_page_url":"http://publications.lib.chalmers.se/publication/15277-a-pitch-synchronous-feature-extraction-method-for-speaker-recognition","pdf_url":null,"source":{"id":"https://openalex.org/S4377196470","display_name":"Chalmers Publication Library (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text.Article.Conference.PeerReviewed"},{"id":"pmh:oai:research.chalmers.se:15277","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/15277","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W2069883713","https://openalex.org/W2113810833","https://openalex.org/W2144115296","https://openalex.org/W2146320039","https://openalex.org/W2164373835","https://openalex.org/W2165880886","https://openalex.org/W3149530262"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W1963976507","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2359140082"],"abstract_inverted_index":{"The":[0,16],"paper":[1],"presents":[2],"a":[3,23,33,58],"novel":[4],"feature":[5,18],"extraction":[6],"method":[7],"to":[8,36],"improve":[9],"the":[10,20,46,52,68,71,76,96],"performance":[11,69],"of":[12,22,51,70],"speaker":[13,88],"identification":[14,89],"systems.":[15],"proposed":[17,97],"has":[19],"form":[21],"typical":[24],"conventional":[25],"feature,":[26,73],"Mel":[27],"frequency":[28],"cepstral":[29,77],"coefficients":[30],"(MFCC),":[31],"but":[32],"flexible":[34],"segmentation":[35],"reduce":[37],"spectral":[38],"mismatch":[39],"between":[40,79],"training":[41,80],"and":[42,48,81,83,93,101],"testing":[43,82],"processes.":[44],"Specifically,":[45],"length":[47],"shift":[49],"size":[50],"analysis":[53],"frame":[54],"are":[55],"determined":[56],"by":[57],"pitch":[59,62],"synchronous":[60,63],"method,":[61],"MFCC":[64],"(PSMFCC).":[65],"To":[66],"verify":[67],"new":[72],"we":[74],"measure":[75],"distortion":[78],"also":[84],"perform":[85],"closed":[86],"set":[87],"tests.":[90],"With":[91],"text-independent":[92],"text-dependent":[94],"experiments,":[95],"algorithm":[98],"provides":[99],"44.3%":[100],"26.7%":[102],"relative":[103],"improvement,":[104],"respectively.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}