{"id":"https://openalex.org/W2146970321","doi":"https://doi.org/10.1109/icassp.2012.6288794","title":"Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise","display_name":"Cepstral analysis based on the glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2146970321","doi":"https://doi.org/10.1109/icassp.2012.6288794","mag":"2146970321"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/84010373-835a-4ca8-893a-95e12b83cb4f","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":[{"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":["The Centre for Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#"],"raw_orcid":null,"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/A5110289715","display_name":"Ranniery Maia","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":"Ranniery Maia","raw_affiliation_strings":["Cambridge Research Laboratory, Toshiba Research Europe Limited, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"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, UK","The Centre for Speech Technology Research, University of Edinburgh, UK#TAB#"],"raw_orcid":null,"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/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#"],"raw_orcid":null,"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":"last","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"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":"Heiga Zen","raw_affiliation_strings":["Cambridge Research Laboratory, Toshiba Research Europe Limited, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7245,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93012079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":null,"first_page":"3997","last_page":"4000"},"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":0.9966999888420105,"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":0.8293265700340271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7385029792785645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7211065292358398},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5909823179244995},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.520622730255127},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5161577463150024},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4789774417877197},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46431800723075867},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45107924938201904},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43491101264953613},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.42533785104751587},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4210319221019745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3512458801269531},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.24808365106582642},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22183316946029663},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08541259169578552},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.07565927505493164}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8293265700340271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7385029792785645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211065292358398},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5909823179244995},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.520622730255127},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5161577463150024},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4789774417877197},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46431800723075867},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45107924938201904},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43491101264953613},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.42533785104751587},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4210319221019745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3512458801269531},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.24808365106582642},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22183316946029663},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08541259169578552},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.07565927505493164},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2012.6288794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.249.1298","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.249.1298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/Cassia_ICASSP12.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/84010373-835a-4ca8-893a-95e12b83cb4f","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/84010373-835a-4ca8-893a-95e12b83cb4f","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/84010373-835a-4ca8-893a-95e12b83cb4f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/84010373-835a-4ca8-893a-95e12b83cb4f","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini-Botinhao, C, Maia, R, Yamagishi, J, King, S & Zen, H 2012, Cepstral analysis based on the Glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise. in 2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) : Kyoto, Japan. IEEE International Conference on Acoustics Speech and Signal Processing, Institute of Electrical and Electronics Engineers, NEW YORK, pp. 3997-4000, IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, 25/03/12. https://doi.org/10.1109/ICASSP.2012.6288794","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/84010373-835a-4ca8-893a-95e12b83cb4f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/84010373-835a-4ca8-893a-95e12b83cb4f","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini-Botinhao, C, Maia, R, Yamagishi, J, King, S & Zen, H 2012, Cepstral analysis based on the Glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise. in 2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) : Kyoto, Japan. IEEE International Conference on Acoustics Speech and Signal Processing, Institute of Electrical and Electronics Engineers, NEW YORK, pp. 3997-4000, IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, 25/03/12. https://doi.org/10.1109/ICASSP.2012.6288794","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"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":12,"referenced_works":["https://openalex.org/W1545406001","https://openalex.org/W1564152904","https://openalex.org/W1588479472","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2075076415","https://openalex.org/W2115039802","https://openalex.org/W2136442985","https://openalex.org/W2141710098","https://openalex.org/W2149948223","https://openalex.org/W6632590417","https://openalex.org/W6677254419"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"In":[0],"this":[1,93],"paper":[2],"we":[3,67],"introduce":[4],"a":[5,111],"new":[6,25,94],"cepstral":[7],"coefficient":[8],"extraction":[9,79],"method":[10,26,80,95,126],"based":[11],"on":[12],"an":[13,74],"intelligibility":[14,31,130],"measure":[15,61],"for":[16,110],"speech":[17,33,86,133,135],"in":[18,34,44,83,134],"noise,":[19],"the":[20,30,38,58,84,97,102,105,124],"Glimpse":[21,59],"Proportion":[22,60],"measure.":[23],"This":[24],"aims":[27],"to":[28,70,101],"increase":[29],"of":[32,104,131],"noise":[35,106],"by":[36],"modifying":[37],"clean":[39],"speech,":[40],"and":[41,50,63,107,116],"has":[42],"applications":[43],"scenarios":[45],"such":[46],"as":[47],"public":[48],"announcement":[49],"car":[51],"navigation":[52],"systems.":[53],"We":[54,89],"first":[55],"explain":[56],"how":[57,66,92],"operates":[62],"further":[64],"show":[65,108],"approximated":[68],"it":[69,72],"integrate":[71],"into":[73],"existing":[75],"spectral":[76],"envelope":[77],"parameter":[78],"commonly":[81],"used":[82],"HMM-based":[85,117],"synthesis":[87],"framework.":[88],"then":[90],"demonstrate":[91],"changes":[96],"modelled":[98],"spectrum":[99],"according":[100],"characteristics":[103],"results":[109],"listening":[112],"test":[113,121],"with":[114],"vocoded":[115],"synthetic":[118,132],"speech.":[119],"The":[120],"indicates":[122],"that":[123],"proposed":[125],"can":[127],"significantly":[128],"improve":[129],"shaped":[136],"noise.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}