{"id":"https://openalex.org/W1544516254","doi":"https://doi.org/10.1109/icassp.2015.7178766","title":"Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech","display_name":"Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1544516254","doi":"https://doi.org/10.1109/icassp.2015.7178766","mag":"1544516254"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5038417409","display_name":"Thomas Merritt","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":true,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]},{"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"]},{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":["Toshiba Research Europe Ltd., Cambridge Research Lab, Cambridge, UK","Toshiba Research Europe Ltd., Cambridge Research Lab, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd., Cambridge Research Lab, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Research Europe Ltd., Cambridge Research Lab, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","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, UK","The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038417409"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":5.6088,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95878517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"4220","last_page":"4224"},"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":0.998199999332428,"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/T12031","display_name":"Speech and dialogue systems","score":0.9930999875068665,"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/naturalness","display_name":"Naturalness","score":0.9047243595123291},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8202345967292786},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.8037929534912109},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7933220863342285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521597743034363},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.551119863986969},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.42001938819885254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40061813592910767},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34855616092681885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17930814623832703}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9047243595123291},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8202345967292786},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8037929534912109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7933220863342285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521597743034363},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.551119863986969},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.42001938819885254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40061813592910767},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34855616092681885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17930814623832703},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"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"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1514737389","https://openalex.org/W1563645159","https://openalex.org/W1564657563","https://openalex.org/W1966083358","https://openalex.org/W1974520683","https://openalex.org/W2000513720","https://openalex.org/W2078597717","https://openalex.org/W2094351325","https://openalex.org/W2095723991","https://openalex.org/W2098372067","https://openalex.org/W2108048146","https://openalex.org/W2111284386","https://openalex.org/W2119929864","https://openalex.org/W2120649056","https://openalex.org/W2129142580","https://openalex.org/W2154920538","https://openalex.org/W2158972663","https://openalex.org/W2188827208","https://openalex.org/W2296704011","https://openalex.org/W2396043161","https://openalex.org/W2401318443","https://openalex.org/W2495084345","https://openalex.org/W2915960560","https://openalex.org/W2916535084","https://openalex.org/W2917245127","https://openalex.org/W3140795192","https://openalex.org/W4205622916","https://openalex.org/W4246354968","https://openalex.org/W6674546848","https://openalex.org/W6675901527","https://openalex.org/W6677973343","https://openalex.org/W6687241212","https://openalex.org/W6697285287","https://openalex.org/W6713281572","https://openalex.org/W6723635755"],"related_works":["https://openalex.org/W1949369849","https://openalex.org/W4391272374","https://openalex.org/W2621401062","https://openalex.org/W2312868712","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473"],"abstract_inverted_index":{"Even":[0],"the":[1,11,34,50,54,57,92,139,142],"best":[2],"statistical":[3],"parametric":[4],"speech":[5,25,32,89],"synthesis":[6,40,136],"systems":[7],"do":[8],"not":[9],"achieve":[10],"naturalness":[12,140],"of":[13,21,46,56,101,134,141],"good":[14],"unit":[15],"selection.":[16],"We":[17,48,128],"investigated":[18,43],"possible":[19],"causes":[20],"this.":[22],"By":[23],"constructing":[24],"signals":[26],"that":[27],"lie":[28],"in":[29],"between":[30],"natural":[31,69,93],"and":[33,53,70,83],"output":[35,76],"from":[36,77,84,118],"a":[37,78,122],"complete":[38],"HMM":[39,135],"system,":[41],"we":[42,120],"various":[44],"effects":[45],"modelling.":[47],"manipulated":[49],"temporal":[51],"smoothness":[52],"variance":[55],"spectral":[58,104],"parameters":[59],"to":[60,66],"create":[61],"stimuli,":[62],"then":[63],"presented":[64],"these":[65],"listeners":[67],"alongside":[68],"vocoded":[71],"speech,":[72],"as":[73,75],"well":[74],"full":[79],"HMM-based":[80],"text-to-speech":[81],"system":[82],"an":[85],"idealised":[86],"`pseudo-HMM'.":[87],"All":[88],"signals,":[90],"except":[91],"waveform,":[94],"were":[95],"created":[96],"using":[97,125],"vocoders":[98],"employing":[99],"one":[100],"two":[102],"popular":[103],"parameterisations:":[105],"Mel-Cepstra":[106],"or":[107,114],"Mel-Line":[108],"Spectral":[109],"Pairs.":[110],"Listeners":[111],"made":[112],"`same":[113],"different'":[115],"pairwise":[116],"judgements,":[117],"which":[119,132],"generated":[121],"perceptual":[123],"map":[124],"Multidimensional":[126],"Scaling.":[127],"draw":[129],"conclusions":[130],"about":[131],"aspects":[133],"are":[137],"limiting":[138],"synthetic":[143],"speech.":[144]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}