{"id":"https://openalex.org/W2953520057","doi":null,"title":"Exploring sub-band cepstral distances for more robust speaker classification","display_name":"Exploring sub-band cepstral distances for more robust speaker classification","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2953520057","mag":"2953520057"},"language":"en","primary_location":{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/164346","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1885/164346","pdf_url":"http://hdl.handle.net/1885/164346","source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 17th Australasian International Conference on Speech Science and Technology","raw_type":"Conference paper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1885/164346","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062046869","display_name":"Takashi Osanai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76259142","display_name":"National Research Institute of Police Science","ror":"https://ror.org/03g9ek587","country_code":"JP","type":"government","lineage":["https://openalex.org/I4405283201","https://openalex.org/I76259142"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Osanai","raw_affiliation_strings":["NATIONAL RESEARCH INSTITUTE OF POLICE SCIENCE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NATIONAL RESEARCH INSTITUTE OF POLICE SCIENCE","institution_ids":["https://openalex.org/I76259142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003623086","display_name":"Yuko Kinoshita","orcid":"https://orcid.org/0000-0001-6820-1421","observed_orcids":["https://orcid.org/0000-0001-6820-1421"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuko Kinoshita","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6820-1421","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110305176","display_name":"Frantz Clermont","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frantz Clermont","raw_affiliation_strings":["French Associates Forensic Lab, England"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"French Associates Forensic Lab, England","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18350801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9463000297546387,"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":0.9463000297546387,"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":0.022199999541044235,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subband-decomposition","display_name":"subband decomposition","score":0.6830000281333923},{"id":"https://openalex.org/keywords/speaker-classification","display_name":"speaker classification","score":0.8740000128746033},{"id":"https://openalex.org/keywords/forensic-voice-comparison","display_name":"forensic voice comparison","score":0.9900000095367432},{"id":"https://openalex.org/keywords/japanese-vowels","display_name":"Japanese vowels","score":0.8989999890327454},{"id":"https://openalex.org/keywords/formants","display_name":"formants","score":0.9480000138282776},{"id":"https://openalex.org/keywords/articulatory-features","display_name":"articulatory features","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5440501570701599},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49105262756347656},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.42860332131385803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39228498935699463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35615161061286926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32763153314590454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.1759522259235382}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/164346","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1885/164346","pdf_url":"http://hdl.handle.net/1885/164346","source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 17th Australasian International Conference on Speech Science and Technology","raw_type":"Conference paper"},{"id":"mag:2953520057","doi":null,"is_oa":false,"landing_page_url":"https://openresearch-repository.anu.edu.au/bitstream/1885/164346/2/01_Osanai_Exploring_sub-band_cepstral_2018.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/164346","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1885/164346","pdf_url":"http://hdl.handle.net/1885/164346","source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 17th Australasian International Conference on Speech Science and Technology","raw_type":"Conference paper"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1873554678","display_name":"Detection of synthetic voice and character identification for estimation of products.","funder_award_id":"18H01671","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5192310523","display_name":"Research on speaker recognition method that is robust to the differences in speaking styles and timing of recording speech using the Standardized-Normalization Transformation","funder_award_id":"25350488","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953520057.pdf","grobid_xml":"https://content.openalex.org/works/W2953520057.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2021150978","https://openalex.org/W2044698521","https://openalex.org/W2064897374","https://openalex.org/W2071861493","https://openalex.org/W2087046691","https://openalex.org/W2105393821","https://openalex.org/W2147841682","https://openalex.org/W2214867628","https://openalex.org/W2997828524"],"related_works":["https://openalex.org/W2956086904","https://openalex.org/W4292068685","https://openalex.org/W4409161325","https://openalex.org/W2220468589","https://openalex.org/W2058745448","https://openalex.org/W3096330096","https://openalex.org/W7099010448","https://openalex.org/W3217766325","https://openalex.org/W2554948384","https://openalex.org/W2234754180"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,9,53,84,93],"first":[4],"of":[5,11,41,55,103],"two-part":[6],"exploration":[7],"into":[8],"potential":[10,105],"parametric":[12],"cepstral":[13],"distance":[14],"(PCD)":[15],"as":[16],"a":[17,88],"forensic":[18],"voice":[19],"comparison":[20],"feature,":[21],"based":[22],"on":[23],"Japanese":[24],"vowel":[25],"data":[26],"collected":[27],"from":[28],"306":[29],"male":[30],"native":[31],"speakers":[32],"under":[33],"microphone":[34],"and":[35,50,78],"mobile":[36],"transmission":[37],"conditions.":[38],"The":[39],"behaviours":[40],"PCDs":[42,56,69],"were":[43],"closely":[44],"examined":[45],"by":[46],"altering":[47],"sub-band":[48,77],"settings,":[49],"we":[51],"found":[52],"behaviour":[54],"to":[57,60,72,87],"correspond":[58],"well":[59],"what":[61],"is":[62],"known":[63],"about":[64],"formants,":[65],"which":[66],"suggests":[67],"that":[68,82],"are":[70],"relatable":[71],"articulatory":[73],"gestures.":[74],"Comparison":[75],"between":[76],"full-band":[79],"PCD":[80],"revealed":[81],"limiting":[83],"band":[85],"range":[86],"specific":[89],"frequency":[90],"region":[91],"makes":[92],"feature":[94],"more":[95],"robust":[96],"against":[97],"channel":[98],"mismatch,":[99],"encouraging":[100],"further":[101],"examination":[102],"this":[104],"feature.":[106]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-07-12T00:00:00"}