{"id":"https://openalex.org/W2138878452","doi":"https://doi.org/10.21437/interspeech.2012-135","title":"Synthetic speech discrimination using pitch pattern statistics derived from image analysis","display_name":"Synthetic speech discrimination using pitch pattern statistics derived from image analysis","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2138878452","doi":"https://doi.org/10.21437/interspeech.2012-135","mag":"2138878452"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-135","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/b2846405-b98b-4857-8cb4-417b78caa373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030748919","display_name":"Phillip L. De Leon","orcid":"https://orcid.org/0000-0002-7665-9632"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Phillip L. De Leon","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109203546","display_name":"Bryan Stewart","orcid":null},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Stewart","raw_affiliation_strings":["New Mexico State University, "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Mexico State University, ","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics, Institute of Language, Cognition and Computation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Institute of Language, Cognition and Computation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6346,"has_fulltext":true,"cited_by_count":66,"citation_normalized_percentile":{"value":0.96667026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"370","last_page":"373"},"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":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7317622303962708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7217334508895874},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5578852891921997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354002118110657},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4928746223449707},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.4569024443626404},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44891414046287537},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4479420483112335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3846367299556732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7317622303962708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7217334508895874},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5578852891921997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354002118110657},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4928746223449707},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.4569024443626404},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44891414046287537},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4479420483112335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3846367299556732},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2012-135","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b2846405-b98b-4857-8cb4-417b78caa373","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.research.ed.ac.uk/en/publications/b2846405-b98b-4857-8cb4-417b78caa373","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b2846405-b98b-4857-8cb4-417b78caa373","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b2846405-b98b-4857-8cb4-417b78caa373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Leon, P L D, Stewart, B & Yamagishi, J 2012, Synthetic Speech Discrimination using Pitch Pattern Statistics Derived from Image Analysis. in Proc. Interspeech : Portland, Oregon, USE.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b2846405-b98b-4857-8cb4-417b78caa373","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/b2846405-b98b-4857-8cb4-417b78caa373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Leon, P L D, Stewart, B & Yamagishi, J 2012, Synthetic Speech Discrimination using Pitch Pattern Statistics Derived from Image Analysis. in Proc. Interspeech : Portland, Oregon, USE.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/b2846405-b98b-4857-8cb4-417b78caa373","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.research.ed.ac.uk/en/publications/b2846405-b98b-4857-8cb4-417b78caa373","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.550000011920929},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2138878452.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1601669156","https://openalex.org/W1707026573","https://openalex.org/W1969876212","https://openalex.org/W2053019885","https://openalex.org/W2112659417","https://openalex.org/W2117418893","https://openalex.org/W2117544888","https://openalex.org/W2119929864","https://openalex.org/W2165143604","https://openalex.org/W2566806337","https://openalex.org/W2917245127"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2152945827","https://openalex.org/W1909292483","https://openalex.org/W114226241","https://openalex.org/W2015513221"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"extend":[4],"the":[5,110,125,130,144,150,162],"work":[6],"by":[7],"Ogihara,":[8],"et":[9],"al.":[10],"to":[11,40,89],"discriminate":[12],"between":[13,32],"human":[14,33,45,90,122,141,174],"and":[15,34,60,84,92,112,121,154,176],"synthetic":[16,35,47,76,106,147,155,182],"speech":[17,36,42,91,107,123,142,148,156,175],"using":[18,52,105,140],"features":[19,63,79],"based":[20],"on":[21,132,161],"pitch":[22,30,54,57,69],"patterns.":[23,70],"As":[24],"previously":[25,138],"demonstrated,":[26],"significant":[27],"differences":[28],"in":[29,48,81,171,179],"patterns":[31],"can":[37],"be":[38],"leveraged":[39],"classify":[41],"as":[43,62,87],"being":[44],"or":[46],"origin.":[49],"We":[50,71,128],"propose":[51],"mean":[53,56],"stability,":[55],"stability":[58],"range,":[59],"jitter":[61],"extracted":[64],"after":[65],"image":[66],"analysis":[67],"of":[68],"have":[72,93],"observed":[73],"that":[74],"for":[75],"speech,":[77],"these":[78],"lie":[80],"a":[82,97,133],"small":[83],"distinct":[85],"space":[86],"compared":[88],"modeled":[94],"them":[95],"with":[96,117],"multivariate":[98],"Gaussian":[99],"distribution.":[100],"Our":[101],"classifier":[102,131],"is":[103],"trained":[104,160],"collected":[108],"from":[109,124,143,149,158],"2008":[111],"2011":[113],"Blizzard":[114],"Challenge":[115],"along":[116],"Festival":[118,159],"pre-built":[119],"voices":[120],"NIST2002":[126],"corpus.":[127,166],"evaluate":[129],"much":[134],"larger":[135],"corpus":[136],"than":[137],"studied":[139],"Switchboard":[145],"corpus,":[146,153],"Resource":[151],"Management":[152],"generated":[157],"Wall":[163],"Street":[164],"Journal":[165],"Results":[167],"show":[168],"98%":[169],"accuracy":[170,178],"correctly":[172,180],"classifying":[173,181],"96%":[177],"speech.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}