{"id":"https://openalex.org/W1666286690","doi":"https://doi.org/10.21437/interspeech.2012-196","title":"Mel cepstral coefficient modification based on the glimpse proportion measure for improving the intelligibility of HMM-generated synthetic speech in noise","display_name":"Mel cepstral coefficient modification based on the glimpse proportion measure for improving the intelligibility of HMM-generated synthetic speech in noise","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W1666286690","doi":"https://doi.org/10.21437/interspeech.2012-196","mag":"1666286690"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-196","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/b5dcc194-5d70-4f16-abd4-cc032d311f24","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"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":["School of Philosophy Psychology and Language Sciences"],"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019012876"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.467,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94351425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"631","last_page":"634"},"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":0.9993000030517578,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7654685378074646},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7448800206184387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7053719758987427},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5958200693130493},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5730732679367065},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.519483208656311},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49155673384666443},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45708656311035156},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.452497661113739},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.449759840965271},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41145193576812744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28907468914985657},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.28716230392456055},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.22125393152236938}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7654685378074646},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7448800206184387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053719758987427},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5958200693130493},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5730732679367065},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.519483208656311},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49155673384666443},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45708656311035156},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.452497661113739},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.449759840965271},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41145193576812744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28907468914985657},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28716230392456055},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22125393152236938},{"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2012-196","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/b5dcc194-5d70-4f16-abd4-cc032d311f24","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/b5dcc194-5d70-4f16-abd4-cc032d311f24","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/b5dcc194-5d70-4f16-abd4-cc032d311f24","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b5dcc194-5d70-4f16-abd4-cc032d311f24","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini-Botinhao, C, Yamagishi, J & King, S 2012, Mel cepstral coefficient modification based on the Glimpse Proportion measure for improving the intelligibility of HMM-generated synthetic speech in noise. in Proc. Interspeech.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/b5dcc194-5d70-4f16-abd4-cc032d311f24","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b5dcc194-5d70-4f16-abd4-cc032d311f24","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini-Botinhao, C, Yamagishi, J & King, S 2012, Mel cepstral coefficient modification based on the Glimpse Proportion measure for improving the intelligibility of HMM-generated synthetic speech in noise. in Proc. Interspeech.","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W198777111","https://openalex.org/W1588479472","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2075076415","https://openalex.org/W2093450784","https://openalex.org/W2146970321","https://openalex.org/W2153185504","https://openalex.org/W2199505332","https://openalex.org/W2401725871"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W1986772939","https://openalex.org/W2160511961"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,27,33,99,123,159],"method":[3,37,87,130,149,171],"that":[4,128],"modifies":[5],"the":[6,18,21,30,47,57,72,78,82,86,113,147,152,163,169],"Mel":[7,58],"cepstral":[8,59],"coefficients":[9,60],"of":[10,20,32,74,81],"HMM-generated":[11],"synthetic":[12,138],"speech":[13,23,96,109,145],"in":[14,29],"order":[15],"to":[16,55,70,136,158],"increase":[17],"intelligibility":[19,133],"generated":[22],"when":[24,134],"heard":[25],"by":[26,76,112],"listener":[28],"presence":[31],"known":[34],"noise.":[35],"This":[36],"is":[38],"based":[39],"on":[40],"an":[41,65],"approximation":[42],"we":[43,52,88],"previously":[44],"proposed":[45,148,170],"for":[46,151],"Glimpse":[48],"Proportion":[49],"measure.":[50],"Here":[51],"show":[53],"how":[54,69],"update":[56],"using":[61,161],"this":[62],"measure":[63],"as":[64],"optimization":[66],"criterion":[67],"and":[68,121],"control":[71],"amount":[73],"distortion":[75],"limiting":[77],"frequency":[79],"resolution":[80],"modifications.":[83],"To":[84],"evaluate":[85],"built":[89,106,142],"eight":[90],"different":[91],"voices":[92,103,141],"from":[93,98,107,143,166],"normal":[94],"read-text":[95],"data":[97,110],"male":[100],"speaker.":[101,115],"Some":[102],"were":[104],"also":[105],"Lombard":[108,144,167],"produced":[111],"same":[114],"Listening":[116],"experiments":[117],"with":[118,122],"speech-shaped":[119],"noise":[120],"single":[124],"competing":[125,153],"talker":[126,154],"indicate":[127],"our":[129],"significantly":[131],"improves":[132],"compared":[135,157],"unmodified":[137],"speech.":[139],"The":[140],"outperformed":[146],"particularly":[150],"case.":[155],"However,":[156],"voice":[160],"only":[162],"spectral":[164],"parameters":[165],"speech,":[168],"obtains":[172],"similar":[173],"or":[174],"higher":[175],"performance.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}