{"id":"https://openalex.org/W2158197208","doi":"https://doi.org/10.1109/icassp.2014.6853602","title":"Cluster adaptive training of average voice models","display_name":"Cluster adaptive training of average voice models","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2158197208","doi":"https://doi.org/10.1109/icassp.2014.6853602","mag":"2158197208"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031222393","display_name":"Vincent Wan","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":true,"raw_author_name":"Vincent Wan","raw_affiliation_strings":["Toshiba Research Europe Ltd., Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","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":"Javier Latorre","raw_affiliation_strings":["Toshiba Research Europe Ltd., Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"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":"Kayoko Yanagisawa","raw_affiliation_strings":["Toshiba Research Europe Ltd., Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"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":"Mark Gales","raw_affiliation_strings":["Toshiba Research Europe Ltd., Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","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":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Ltd., Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031222393"],"corresponding_institution_ids":["https://openalex.org/I4210143477"],"apc_list":null,"apc_paid":null,"fwci":0.818,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81765535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"284"},"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":0.9973999857902527,"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":0.9919999837875366,"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":0.7187197208404541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7042402029037476},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6364874839782715},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5681411027908325},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5336991548538208},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45751944184303284},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4430263936519623},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4286717474460602},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.42523878812789917},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41506439447402954},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4143199622631073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38018304109573364},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.21027463674545288},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16614633798599243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13241228461265564},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0684359073638916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7187197208404541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7042402029037476},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6364874839782715},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5681411027908325},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5336991548538208},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45751944184303284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4430263936519623},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4286717474460602},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.42523878812789917},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41506439447402954},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4143199622631073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38018304109573364},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.21027463674545288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16614633798599243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13241228461265564},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0684359073638916},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W80543058","https://openalex.org/W102093577","https://openalex.org/W126988493","https://openalex.org/W193437634","https://openalex.org/W333180468","https://openalex.org/W344150399","https://openalex.org/W1523817494","https://openalex.org/W1935012542","https://openalex.org/W1953949349","https://openalex.org/W2002342963","https://openalex.org/W2025638820","https://openalex.org/W2069631319","https://openalex.org/W2114659828","https://openalex.org/W2131650634","https://openalex.org/W2140567543","https://openalex.org/W2153914468","https://openalex.org/W2165108269","https://openalex.org/W2169878657","https://openalex.org/W2269105564","https://openalex.org/W2283817422","https://openalex.org/W3031363333","https://openalex.org/W6603264027","https://openalex.org/W6611394673","https://openalex.org/W6611766843"],"related_works":["https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2194396582","https://openalex.org/W2082284720","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2379938888"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1],"model":[2,22,72],"based":[3],"text-to-speech":[4],"systems":[5],"may":[6,80],"be":[7,81],"adapted":[8],"so":[9],"that":[10,93],"the":[11,73,89,94,109],"synthesised":[12],"speech":[13,67,110],"sounds":[14],"like":[15],"a":[16,45,52,84],"particular":[17],"person.":[18],"The":[19,77],"average":[20],"voice":[21],"(AVM)":[23],"approach":[24],"uses":[25],"linear":[26],"transforms":[27],"to":[28],"achieve":[29],"this":[30],"while":[31,108],"multiple":[32],"decision":[33],"tree":[34],"cluster":[35],"adaptive":[36],"training":[37],"(CAT)":[38],"represents":[39],"different":[40],"speakers":[41],"as":[42,83],"points":[43],"in":[44],"low":[46],"dimensional":[47],"space.":[48],"This":[49],"paper":[50],"describes":[51],"novel":[53],"combination":[54,79,95],"of":[55,88],"CAT":[56,62,107],"and":[57,106,115],"AVM":[58,105,114],"for":[59],"modelling":[60],"speakers.":[61],"yields":[63],"higher":[64],"quality":[65,111],"synthetic":[66],"than":[68],"AVMs":[69,71],"but":[70],"target":[74,98],"speaker":[75,99],"better.":[76],"resulting":[78],"interpreted":[82],"more":[85],"powerful":[86],"version":[87],"AVM.":[90],"Results":[91],"show":[92],"achieves":[96],"better":[97],"similarity":[100],"when":[101],"compared":[102],"with":[103],"both":[104],"is":[112],"in-between":[113],"CAT.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}