{"id":"https://openalex.org/W2141710098","doi":"https://doi.org/10.1109/icassp.2011.5947507","title":"Evaluation of objective measures for intelligibility prediction of HMM-based synthetic speech in noise","display_name":"Evaluation of objective measures for intelligibility prediction of HMM-based synthetic speech in noise","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2141710098","doi":"https://doi.org/10.1109/icassp.2011.5947507","mag":"2141710098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"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":"Cassia Valentini-Botinhao","raw_affiliation_strings":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, 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":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"5112","last_page":"5115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8856004476547241},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7234174609184265},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6510734558105469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6377702951431274},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6140105128288269},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49549400806427},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44095373153686523},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.308849036693573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29353421926498413},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1700897216796875},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15320739150047302},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07310649752616882}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8856004476547241},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7234174609184265},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6510734558105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377702951431274},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6140105128288269},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49549400806427},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44095373153686523},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.308849036693573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29353421926498413},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1700897216796875},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15320739150047302},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07310649752616882},{"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":3,"locations":[{"id":"doi:10.1109/icassp.2011.5947507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/a94ba1c1-ec3e-46fd-a2de-30e4720a24cf","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/a94ba1c1-ec3e-46fd-a2de-30e4720a24cf","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":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/a94ba1c1-ec3e-46fd-a2de-30e4720a24cf","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a94ba1c1-ec3e-46fd-a2de-30e4720a24cf","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":"Valentini-Botinhao, C, Yamagishi, J & King, S 2011, Evaluation of objective measures for intelligibility prediction of HMM-based synthetic speech in noise. in Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. pp. 5112-5115. https://doi.org/10.1109/ICASSP.2011.5947507","raw_type":"contributionToPeriodical"}],"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":10,"referenced_works":["https://openalex.org/W1494634987","https://openalex.org/W1552314771","https://openalex.org/W1564152904","https://openalex.org/W1987831012","https://openalex.org/W2015512175","https://openalex.org/W2041777218","https://openalex.org/W2075076415","https://openalex.org/W2129142580","https://openalex.org/W2144404214","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W2166831097","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"In":[0,134],"this":[1,160],"paper":[2],"we":[3,56,137],"evaluate":[4],"four":[5,71],"objective":[6],"measures":[7,75,94,111],"of":[8,15,46,53,60,100,104,116],"speech":[9,17,55,64,120,141],"with":[10,78,102],"regards":[11],"to":[12,95,107],"intelligibility":[13,25,80,117,157],"prediction":[14],"synthesized":[16,54,140],"in":[18,83,129,159],"diverse":[19],"noisy":[20,68],"situations.":[21],"We":[22],"evaluated":[23],"three":[24],"measures,":[26],"the":[27,30,34,43,51,61,89,92,97,131,139,154],"Dau":[28,90],"measure,":[29,42],"glimpse":[31,93],"proportion":[32],"and":[33,39,91],"Speech":[35,47],"Intelligibility":[36],"Index":[37],"(SII)":[38],"a":[40,58],"quality":[41],"Perceptual":[44],"Evaluation":[45],"Quality":[48],"(PESQ).":[49],"For":[50],"generation":[52],"used":[57],"state":[59],"art":[62],"HMM-based":[63],"synthesis":[65],"system.":[66],"The":[67,74,86,150],"conditions":[69],"comprised":[70],"additive":[72],"noises.":[73],"were":[76],"compared":[77],"subjective":[79,108],"scores":[81],"obtained":[82],"listening":[84],"tests.":[85],"results":[87],"show":[88],"be":[96],"best":[98],"predictors":[99],"intelligibility,":[101],"correlations":[103],"around":[105],"0.83":[106],"scores.":[109],"All":[110],"gave":[112,153],"less":[113],"accurate":[114,156],"predictions":[115,158],"for":[118,126],"synthetic":[119],"than":[121],"have":[122],"previously":[123],"been":[124],"found":[125],"natural":[127],"speech;":[128],"particular":[130],"SII":[132],"measure.":[133],"additional":[135],"experiments,":[136],"processed":[138],"by":[142],"an":[143],"ideal":[144],"binary":[145],"mask":[146],"before":[147],"adding":[148],"noise.":[149],"Glimpse":[151],"measure":[152],"most":[155],"situation.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
