{"id":"https://openalex.org/W2156146072","doi":"https://doi.org/10.1109/icassp.2012.6288797","title":"Unsupervised clustering of emotion and voice styles for expressive TTS","display_name":"Unsupervised clustering of emotion and voice styles for expressive TTS","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2156146072","doi":"https://doi.org/10.1109/icassp.2012.6288797","mag":"2156146072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288797","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/A5023264395","display_name":"Florian Eyben","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Florian Eyben","raw_affiliation_strings":["Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004649927","display_name":"Sabine Buchholz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sabine Buchholz","raw_affiliation_strings":["Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075928867","display_name":"Norbert Braunschweiler","orcid":"https://orcid.org/0000-0003-1388-440X"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Norbert Braunschweiler","raw_affiliation_strings":["Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210143477"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4009","last_page":"4012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.7409951686859131},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6770387291908264},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.658318817615509},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5858019590377808},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5780802369117737},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.45035111904144287},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44892048835754395},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42364126443862915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3985234797000885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39290857315063477},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11271610856056213},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08963543176651001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409951686859131},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6770387291908264},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.658318817615509},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5858019590377808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5780802369117737},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.45035111904144287},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44892048835754395},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42364126443862915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3985234797000885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39290857315063477},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11271610856056213},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08963543176651001},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288797","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:generic.eprints.org:521310","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/521310/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W83586041","https://openalex.org/W118315650","https://openalex.org/W1479771596","https://openalex.org/W1517939602","https://openalex.org/W1585610988","https://openalex.org/W2083543775","https://openalex.org/W2085013480","https://openalex.org/W2153914468","https://openalex.org/W2158061940","https://openalex.org/W2158972663","https://openalex.org/W2159290663","https://openalex.org/W2292984643","https://openalex.org/W2294232014","https://openalex.org/W2296199791","https://openalex.org/W2400063444","https://openalex.org/W6600088033","https://openalex.org/W6604792588","https://openalex.org/W6628675675","https://openalex.org/W6630997582","https://openalex.org/W6635035540","https://openalex.org/W6683445396","https://openalex.org/W6697151493","https://openalex.org/W6697163159"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"Current":[0],"text-to-speech":[1],"synthesis":[2,29,79],"(TTS)":[3],"systems":[4],"are":[5,66],"often":[6],"perceived":[7],"as":[8],"lacking":[9],"expressiveness,":[10],"limiting":[11],"the":[12,71,89,98,121],"ability":[13],"to":[14,48],"fully":[15],"convey":[16],"information.":[17],"This":[18],"paper":[19],"describes":[20],"initial":[21],"investigations":[22],"into":[23,60],"improving":[24],"expressiveness":[25,122],"for":[26],"statistical":[27],"speech":[28,78,117,125],"systems.":[30],"Rather":[31],"than":[32,126],"using":[33,81],"hand-crafted":[34],"definitions":[35],"of":[36,51,88,104,123],"expressive":[37],"classes,":[38],"an":[39,61],"unsupervised":[40],"clustering":[41],"approach":[42],"is":[43,46],"described":[44],"which":[45,97],"scalable":[47],"large":[49],"quantities":[50],"training":[52],"data.":[53],"To":[54],"incorporate":[55],"this":[56],"\u201cexpression":[57],"cluster\u201d":[58],"information":[59],"HMM-TTS":[62],"system":[63],"two":[64],"approaches":[65,90],"described:":[67],"cluster":[68],"questions":[69],"in":[70,96,116],"decision":[72],"tree":[73],"construction;":[74],"and":[75],"average":[76],"expression":[77],"(AESS)":[80],"cluster-based":[82],"linear":[83],"transform":[84],"adaptation.":[85],"The":[86],"performance":[87],"was":[91],"evaluated":[92],"on":[93],"audiobook":[94],"data":[95],"reader":[99],"exhibits":[100],"a":[101,127],"wide":[102],"range":[103],"expressiveness.":[105],"A":[106],"subjective":[107],"listening":[108],"test":[109],"showed":[110],"that":[111,118],"synthesising":[112],"with":[113],"AESS":[114],"results":[115],"better":[119],"reflects":[120],"human":[124],"baseline":[128],"expression-independent":[129],"system.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}