{"id":"https://openalex.org/W2059142112","doi":"https://doi.org/10.1109/icassp.2013.6639219","title":"Speaker and language independent voice quality classification applied to unlabelled corpora of expressive speech","display_name":"Speaker and language independent voice quality classification applied to unlabelled corpora of expressive speech","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2059142112","doi":"https://doi.org/10.1109/icassp.2013.6639219","mag":"2059142112"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075897911","display_name":"John Kane","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"John Kane","raw_affiliation_strings":["Phonetics and Speech Laboratory, School of Linguistic, Speech and Communication Sciences, Trinity College Dublin, Ireland","Phonetics & Speech Lab., Trinity Coll. Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonetics and Speech Laboratory, School of Linguistic, Speech and Communication Sciences, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Phonetics & Speech Lab., Trinity Coll. Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080030626","display_name":"Stefan Scherer","orcid":"https://orcid.org/0000-0002-0280-5393"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Scherer","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California, USA","[Inst. for Creative Technol., Univ. of Southern California, Playa Vista, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"]},{"raw_affiliation_string":"[Inst. for Creative Technol., Univ. of Southern California, Playa Vista, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007820415","display_name":"Matthew P. Aylett","orcid":"https://orcid.org/0000-0001-7057-0525"},"institutions":[{"id":"https://openalex.org/I4210104229","display_name":"CereProc (United Kingdom)","ror":"https://ror.org/00vnfjq11","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210104229"]},{"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":"Matthew Aylett","raw_affiliation_strings":["School of Informatics, UK and CereProc Ltd., University of Edinburgh, UK","[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, UK and CereProc Ltd., University of Edinburgh, UK","institution_ids":["https://openalex.org/I4210104229","https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2010Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California, USA","[Inst. for Creative Technol., Univ. of Southern California, Playa Vista, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"]},{"raw_affiliation_string":"[Inst. for Creative Technol., Univ. of Southern California, Playa Vista, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029071500","display_name":"Christer Gobl","orcid":"https://orcid.org/0000-0002-5958-3891"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Christer Gobl","raw_affiliation_strings":["Phonetics and Speech Laboratory, School of Linguistic, Speech and Communication Sciences, Trinity College Dublin, Ireland","Phonetics & Speech Lab., Trinity Coll. Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonetics and Speech Laboratory, School of Linguistic, Speech and Communication Sciences, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Phonetics & Speech Lab., Trinity Coll. Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6609,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94459719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7982","last_page":"7986"},"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":0.9994999766349792,"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":0.9990000128746033,"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":0.8556135892868042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6956747174263},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6086196899414062},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.498990535736084},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4555339813232422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4499640166759491},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4487874507904053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4407280683517456},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4181594252586365},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41760823130607605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556135892868042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6956747174263},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6086196899414062},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.498990535736084},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4555339813232422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4499640166759491},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4487874507904053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4407280683517456},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4181594252586365},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41760823130607605},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.975.1954","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.975.1954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ict.usc.edu/pubs/Speaker%20and%20Language%20Independent%20Voice%20Quality%20Classification%20Applied%20to%20Unlabeled%20Corpora%20of%20Expressive%20Speech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W169745891","https://openalex.org/W181056519","https://openalex.org/W1483501585","https://openalex.org/W1509608124","https://openalex.org/W1517939602","https://openalex.org/W1541208205","https://openalex.org/W1625928172","https://openalex.org/W1970314771","https://openalex.org/W1980801609","https://openalex.org/W2021320575","https://openalex.org/W2024590593","https://openalex.org/W2057777629","https://openalex.org/W2064990378","https://openalex.org/W2078950386","https://openalex.org/W2082018710","https://openalex.org/W2097634052","https://openalex.org/W2103039612","https://openalex.org/W2104773730","https://openalex.org/W2107449214","https://openalex.org/W2109020278","https://openalex.org/W2109138290","https://openalex.org/W2113516703","https://openalex.org/W2125514156","https://openalex.org/W2153903782","https://openalex.org/W2295471129","https://openalex.org/W2397375888","https://openalex.org/W2401969501","https://openalex.org/W2578611706","https://openalex.org/W3009530327","https://openalex.org/W3049768459","https://openalex.org/W4285719527","https://openalex.org/W4390912420","https://openalex.org/W6674913099","https://openalex.org/W6697155323","https://openalex.org/W6712344080","https://openalex.org/W6732313247","https://openalex.org/W6774797194","https://openalex.org/W6781122186","https://openalex.org/W6860722923"],"related_works":["https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793","https://openalex.org/W2110108310","https://openalex.org/W2349468610"],"abstract_inverted_index":{"Voice":[0],"quality":[1,16,43,102],"plays":[2],"a":[3,83,120],"pivotal":[4],"role":[5],"in":[6,104,123],"speech":[7,23,47,52,125],"style":[8],"variation.":[9],"Therefore,":[10],"control":[11],"and":[12,63,81],"analysis":[13,44],"of":[14,22,85,93],"voice":[15,42,87,101],"is":[17,61],"critical":[18],"for":[19,50],"many":[20],"areas":[21],"technology.":[24],"Until":[25],"now,":[26],"most":[27],"work":[28],"has":[29],"focused":[30],"on":[31],"small":[32],"purpose":[33],"built":[34,49],"corpora.":[35,70],"In":[36],"this":[37,74],"paper":[38],"we":[39],"apply":[40,73],"state-of-the-art":[41],"to":[45,76,99],"large":[46],"corpora":[48,110],"expressive":[51,124],"synthesis.":[53,126],"A":[54],"fuzzy-input":[55],"fuzzy-output":[56],"support":[57],"vector":[58],"machine":[59],"classifier":[60,75],"trained":[62],"validated":[64],"using":[65],"features":[66],"extracted":[67],"from":[68],"these":[69,105],"We":[71],"then":[72],"freely":[77],"available":[78,107],"audiobook":[79,109],"data":[80],"demonstrate":[82],"clustering":[84],"the":[86,91,113],"qualities":[88],"that":[89,112],"approximates":[90],"performance":[92],"human":[94],"perceptual":[95],"ratings.":[96],"The":[97],"ability":[98],"detect":[100],"variation":[103],"widely":[106],"unlabelled":[108],"means":[111],"proposed":[114],"method":[115],"may":[116],"be":[117],"used":[118],"as":[119],"valuable":[121],"resource":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
