{"id":"https://openalex.org/W2026490135","doi":"https://doi.org/10.1109/icassp.2013.6639220","title":"Lightly supervised GMM VAD to use audiobook for speech synthesiser","display_name":"Lightly supervised GMM VAD to use audiobook for speech synthesiser","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2026490135","doi":"https://doi.org/10.1109/icassp.2013.6639220","mag":"2026490135"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639220","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":"article","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/A5000153508","display_name":"Yoshitaka Mamiya","orcid":null},"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":"Yoshitaka Mamiya","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"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":"Junichi Yamagishi","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"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":"Oliver Watts","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084488961","display_name":"Robert A. Clark","orcid":"https://orcid.org/0000-0002-4892-3619"},"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":"Robert A.J. Clark","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"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":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Universitatea Tehnica din Cluj-Napoca, Cluj-Napoca, RO","Commun. Dept., Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitatea Tehnica din Cluj-Napoca, Cluj-Napoca, RO","institution_ids":["https://openalex.org/I158333966"]},{"raw_affiliation_string":"Commun. Dept., Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9295,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95872392,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7987","last_page":"7991"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.8217037916183472},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6935827732086182},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6068070530891418},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5610764622688293},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5289171934127808},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.5076969861984253},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4815962016582489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45482590794563293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4193335175514221},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07770827412605286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217037916183472},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6935827732086182},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6068070530891418},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5610764622688293},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5289171934127808},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.5076969861984253},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4815962016582489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45482590794563293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4193335175514221},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07770827412605286},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2013.6639220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639220","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:10.1.1.395.9833","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.9833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2013/0007987.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/eefa6ca1-8d86-4370-b5d5-aed4bcf2ca73","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eefa6ca1-8d86-4370-b5d5-aed4bcf2ca73","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2533495","https://openalex.org/W118315650","https://openalex.org/W1517939602","https://openalex.org/W1577300430","https://openalex.org/W1583620810","https://openalex.org/W2054442733","https://openalex.org/W2073693905","https://openalex.org/W2103738385","https://openalex.org/W2107457864","https://openalex.org/W2115717467","https://openalex.org/W2119564743","https://openalex.org/W2135445137","https://openalex.org/W2142170306","https://openalex.org/W2145880678","https://openalex.org/W2147760966","https://openalex.org/W2283817422","https://openalex.org/W2294232014","https://openalex.org/W2296111744","https://openalex.org/W2350261514","https://openalex.org/W2395301602","https://openalex.org/W2396127172","https://openalex.org/W2400063444","https://openalex.org/W6600088033","https://openalex.org/W6604792588","https://openalex.org/W6634448757","https://openalex.org/W6676004468","https://openalex.org/W6681813711","https://openalex.org/W6695760510","https://openalex.org/W6697311706","https://openalex.org/W6711746505","https://openalex.org/W6712575894","https://openalex.org/W6712610176"],"related_works":["https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2605000190","https://openalex.org/W4296069123","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081"],"abstract_inverted_index":{"Audiobooks":[0],"have":[1,18,38,78],"been":[2],"focused":[3],"on":[4,167],"as":[5,106],"promising":[6],"data":[7,47,61],"for":[8,52,83,126],"training":[9],"Text-to-Speech":[10],"(TTS)":[11],"systems.":[12],"However,":[13],"they":[14,27],"usually":[15,29],"do":[16],"not":[17],"a":[19,41,94,107],"correspondence":[20,42],"between":[21],"audio":[22,44,58],"and":[23,45,59,64,87,123],"text":[24,46,60,88],"data.":[25,89],"Moreover,":[26],"are":[28],"divided":[30],"only":[31,125],"into":[32],"chapter":[33],"units.":[34],"In":[35],"practice,":[36],"we":[37,49,77,133,148],"to":[39,80,102],"make":[40],"of":[43,121,162],"before":[48,110],"use":[50,81],"them":[51],"building":[53],"TTS":[54,137],"synthesisers.":[55],"However":[56],"aligning":[57,85],"is":[62],"time-consuming":[63],"involves":[65],"manual":[66,143],"labor.":[67],"It":[68],"also":[69],"requires":[70,118],"persons":[71],"skilled":[72],"in":[73],"speech":[74,86,122,164],"processing.":[75],"Previously,":[76],"proposed":[79,156],"graphemes":[82],"automatically":[84],"This":[90,114],"paper":[91],"further":[92],"integrates":[93],"lightly":[95,115],"supervised":[96,116],"voice":[97],"activity":[98],"detection":[99],"(VAD)":[100],"technique":[101,117,158],"detect":[103],"sentence":[104],"boundaries":[105],"pre-processing":[108],"step":[109],"the":[111,127,151,155,160],"grapheme":[112],"approach.":[113],"time":[119],"stamps":[120],"silence":[124],"first":[128],"fifty":[129],"sentences.":[130],"Combining":[131],"those,":[132],"can":[134],"semi-automatically":[135],"build":[136],"systems":[138],"from":[139],"audiobooks":[140],"with":[141],"minimum":[142],"intervention.":[144],"From":[145],"subjective":[146],"evaluations":[147],"analyse":[149],"how":[150],"grapheme-based":[152],"aligner":[153],"and/or":[154],"VAD":[157],"impact":[159],"quality":[161],"HMM-based":[163],"synthesisers":[165],"trained":[166],"audiobooks.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}