{"id":"https://openalex.org/W2147760966","doi":"https://doi.org/10.1109/icassp.2012.6288941","title":"Detecting a targeted voice style in an audiobook using voice quality features","display_name":"Detecting a targeted voice style in an audiobook using voice quality features","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2147760966","doi":"https://doi.org/10.1109/icassp.2012.6288941","mag":"2147760966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Eva Szekely","raw_affiliation_strings":["CNGL, School of Computer Science and Informatics, University College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNGL, School of Computer Science and Informatics, University College Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","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":["Centre for Language and Communication Studies, Trinity College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language and Communication Studies, Trinity College 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/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":"Stefan Scherer","raw_affiliation_strings":["Centre for Language and Communication Studies, Trinity College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language and Communication Studies, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029071500","display_name":"Christer Gobl","orcid":"https://orcid.org/0000-0002-5958-3891"},"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/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]},{"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":["IE","US"],"is_corresponding":false,"raw_author_name":"Christer Gobl","raw_affiliation_strings":["Centre for Language and Communication Studies, Trinity College Dublin, Ireland","Institute for Creative Technologies, University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language and Communication Studies, Trinity College Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046306415","display_name":"Julie Carson-Berndsen","orcid":"https://orcid.org/0000-0002-1851-3643"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Julie Carson-Berndsen","raw_affiliation_strings":["CNGL, School of Computer Science and Informatics, University College Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNGL, School of Computer Science and Informatics, University College Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8619,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92181115,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4593","last_page":"4596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/speech-recognition","display_name":"Speech recognition","score":0.7322582006454468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724162757396698},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6111487746238708},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5210365653038025},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5098604559898376},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4772772192955017},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4257628321647644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37412816286087036},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17201313376426697},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10418826341629028}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7322582006454468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724162757396698},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6111487746238708},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5210365653038025},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5098604559898376},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4772772192955017},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4257628321647644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37412816286087036},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17201313376426697},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10418826341629028}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.6326","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.6326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cngl.ie/drupal/sites/default/files/papers3/ES_JK_SS_voiceStyle_fixedref_0.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1483501585","https://openalex.org/W1486632395","https://openalex.org/W1493730813","https://openalex.org/W1517939602","https://openalex.org/W2010070470","https://openalex.org/W2022194925","https://openalex.org/W2096760972","https://openalex.org/W2294232014","https://openalex.org/W2295471129","https://openalex.org/W6630997582","https://openalex.org/W6697155323","https://openalex.org/W6697311706"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W3177678247","https://openalex.org/W2174706483","https://openalex.org/W1999617572","https://openalex.org/W1995281866"],"abstract_inverted_index":{"Audiobooks":[0],"are":[1,48,57,63,137],"known":[2],"to":[3,66,79,112,127],"contain":[4],"a":[5,14,20,23,60,75,90,103,128,152],"variety":[6,33],"of":[7,16,31,39,85,105,143],"expressive":[8],"speaking":[9,54],"styles":[10],"that":[11],"occur":[12],"as":[13],"result":[15],"the":[17,37,69,86,114,120,141,144],"narrator":[18],"mimicking":[19],"character":[21],"in":[22,96,116,151],"story,":[24],"or":[25],"expressing":[26],"affect.":[27],"An":[28],"accurate":[29],"modeling":[30],"this":[32],"is":[34,110],"essential":[35],"for":[36,92],"purposes":[38],"speech":[40],"synthesis":[41],"from":[42,68],"an":[43,97,117],"audiobook.":[44],"Voice":[45],"quality":[46,126],"differences":[47],"important":[49],"features":[50,84],"characterizing":[51,77],"these":[52,101],"different":[53],"styles,":[55],"which":[56],"realized":[58],"on":[59,100,140],"gradient":[61],"and":[62,89,107,149],"often":[64],"difficult":[65],"predict":[67],"text.":[70],"The":[71,132],"present":[72],"study":[73],"uses":[74],"parameter":[76],"breathy":[78],"tense":[80],"voice":[81,125,130,134],"qualities":[82],"using":[83],"wavelet":[87],"transform,":[88],"measure":[91],"identifying":[93],"creaky":[94],"segments":[95],"utterance.":[98],"Based":[99],"features,":[102],"combination":[104],"supervised":[106,145],"unsupervised":[108],"classification":[109],"used":[111],"detect":[113],"regions":[115],"audiobook,":[118],"where":[119],"speaker":[121],"changes":[122],"his":[123],"regular":[124],"particular":[129],"style.":[131],"target":[133],"style":[135],"candidates":[136],"selected":[138],"based":[139],"agreement":[142],"classifier":[146],"ensemble":[147],"output,":[148],"evaluated":[150],"listening":[153],"test.":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
