{"id":"https://openalex.org/W142852980","doi":"https://doi.org/10.21437/interspeech.2004-503","title":"Noise-robust speaker verification using F0 features","display_name":"Noise-robust speaker verification using F0 features","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W142852980","doi":"https://doi.org/10.21437/interspeech.2004-503","mag":"142852980"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5084374665","display_name":"Koji Iwano","orcid":"https://orcid.org/0000-0002-7373-5353"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Iwano","raw_affiliation_strings":["Tokyo Inst. of Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Tech","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112536171","display_name":"Taichi Asami","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taichi Asami","raw_affiliation_strings":["Tokyo Inst. of Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Tech","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sadaoki Furui","raw_affiliation_strings":["Tokyo Inst. of Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Tech","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.9251,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80038179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1417","last_page":"1420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987000226974487,"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":0.9718999862670898,"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":0.7463589310646057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6986591815948486},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6657544374465942},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5874608159065247},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5692229866981506},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.565890371799469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5060274004936218},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5046330690383911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49499839544296265},{"id":"https://openalex.org/keywords/hough-transform","display_name":"Hough transform","score":0.4804506003856659},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.461845338344574},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4268527626991272},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41120415925979614},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3860738277435303},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11681464314460754},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10925841331481934},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0580390989780426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7463589310646057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6986591815948486},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6657544374465942},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5874608159065247},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5692229866981506},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.565890371799469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5060274004936218},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5046330690383911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49499839544296265},{"id":"https://openalex.org/C200518788","wikidata":"https://www.wikidata.org/wiki/Q195076","display_name":"Hough transform","level":3,"score":0.4804506003856659},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.461845338344574},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4268527626991272},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41120415925979614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3860738277435303},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11681464314460754},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10925841331481934},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0580390989780426},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2004-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00107091","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100501628","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00107622","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100502190","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W37174524","https://openalex.org/W41029615","https://openalex.org/W51851856","https://openalex.org/W62658503","https://openalex.org/W119457553","https://openalex.org/W1495955104","https://openalex.org/W1593862356","https://openalex.org/W1751091532","https://openalex.org/W2100462743","https://openalex.org/W2104241941","https://openalex.org/W2114851258"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W66821593","https://openalex.org/W2074132948"],"abstract_inverted_index":{"This":[0],"paper":[1,14],"proposes":[2,28],"a":[3,17,29,62],"noise-robust":[4,18],"speaker":[5,31],"verification":[6,32,86],"method":[7,21,33],"augmented":[8],"by":[9,53],"fundamental":[10],"frequency":[11],"(F0).":[12],"The":[13,66],"first":[15],"describes":[16],"F0":[19,41,82],"extraction":[20],"using":[22,34,48],"the":[23,39,81,85],"Hough":[24],"transform.":[25],"Then,":[26],"it":[27],"robust":[30],"multi-stream":[35],"HMMs":[36],"which":[37],"fuse":[38],"extracted":[40],"and":[42],"cepstral":[43],"features.":[44],"Experiments":[45],"are":[46,68],"conducted":[47],"fourconnected-digit":[49],"utterances":[50,67],"of":[51],"Japanese":[52],"37":[54],"male":[55],"speakers":[56],"recorded":[57],"at":[58,73],"five":[59],"sessions":[60],"over":[61],"half":[63],"year":[64],"period.":[65],"contaminated":[69],"with":[70],"white":[71],"noise":[72],"various":[74],"SNR":[75,90],"levels.":[76],"Experimental":[77],"results":[78],"show":[79],"that":[80],"features":[83],"improve":[84],"performance":[87],"in":[88],"all":[89],"conditions.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}