{"id":"https://openalex.org/W1968944773","doi":"https://doi.org/10.1109/icassp.2014.6854810","title":"A fixed dimension and perceptually based dynamic sinusoidal model of speech","display_name":"A fixed dimension and perceptually based dynamic sinusoidal model of speech","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1968944773","doi":"https://doi.org/10.1109/icassp.2014.6854810","mag":"1968944773"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854810","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":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/8b4cdf98-79a6-403c-8a87-4eb24231b843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032437290","display_name":"Qiong Hu","orcid":"https://orcid.org/0000-0002-7525-1387"},"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":"Qiong Hu","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"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":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, UK","Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"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":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","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/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, UK","Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#","institution_ids":["https://openalex.org/I1292669757"]}]},{"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/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, UK","Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur., Ltd., Cambridge, UK#TAB#","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4743,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81443005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"50","issue":null,"first_page":"6270","last_page":"6274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9980999827384949,"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/dimension","display_name":"Dimension (graph theory)","score":0.728939414024353},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6154743432998657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5698297619819641},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5546080470085144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5179818868637085},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.49396759271621704},{"id":"https://openalex.org/keywords/critical-band","display_name":"Critical band","score":0.4423619508743286},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41598665714263916},{"id":"https://openalex.org/keywords/sinusoid","display_name":"Sinusoid","score":0.411876916885376},{"id":"https://openalex.org/keywords/sine-wave","display_name":"Sine wave","score":0.4103609621524811},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3742525577545166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.268233984708786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1595841348171234},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15117043256759644}],"concepts":[{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.728939414024353},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6154743432998657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5698297619819641},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5546080470085144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5179818868637085},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.49396759271621704},{"id":"https://openalex.org/C96390635","wikidata":"https://www.wikidata.org/wiki/Q366708","display_name":"Critical band","level":2,"score":0.4423619508743286},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41598665714263916},{"id":"https://openalex.org/C2776417487","wikidata":"https://www.wikidata.org/wiki/Q103142","display_name":"Sinusoid","level":2,"score":0.411876916885376},{"id":"https://openalex.org/C66907618","wikidata":"https://www.wikidata.org/wiki/Q207527","display_name":"Sine wave","level":3,"score":0.4103609621524811},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3742525577545166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.268233984708786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1595841348171234},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15117043256759644},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2014.6854810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854810","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.432.1543","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.432.1543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2014/Qiong_IC14.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/8b4cdf98-79a6-403c-8a87-4eb24231b843","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8b4cdf98-79a6-403c-8a87-4eb24231b843","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":"Hu, Q, Stylianou, Y, Richmond, K, Maia, R, Yamagishi, J & Latorre, J 2014, A fixed dimension and perceptually based dynamic sinusoidal model of speech. in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on . Institute of Electrical and Electronics Engineers, pp. 6311-6315. https://doi.org/10.1109/ICASSP.2014.6854810","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/8b4cdf98-79a6-403c-8a87-4eb24231b843","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/8b4cdf98-79a6-403c-8a87-4eb24231b843","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/8b4cdf98-79a6-403c-8a87-4eb24231b843","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8b4cdf98-79a6-403c-8a87-4eb24231b843","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":"Hu, Q, Stylianou, Y, Richmond, K, Maia, R, Yamagishi, J & Latorre, J 2014, A fixed dimension and perceptually based dynamic sinusoidal model of speech. in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on . Institute of Electrical and Electronics Engineers, pp. 6311-6315. https://doi.org/10.1109/ICASSP.2014.6854810","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2750010394","display_name":null,"funder_award_id":"EP/I027696/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W95551363","https://openalex.org/W1601809792","https://openalex.org/W1789794644","https://openalex.org/W1975816629","https://openalex.org/W1993822631","https://openalex.org/W1998915416","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2093283533","https://openalex.org/W2096980176","https://openalex.org/W2128301448","https://openalex.org/W2135934764","https://openalex.org/W2164764235","https://openalex.org/W2402513802","https://openalex.org/W6636056872","https://openalex.org/W6638142982"],"related_works":["https://openalex.org/W2364109525","https://openalex.org/W4306957617","https://openalex.org/W2085254699","https://openalex.org/W2021517264","https://openalex.org/W1983945054","https://openalex.org/W1969523285","https://openalex.org/W2089902174","https://openalex.org/W1977687745","https://openalex.org/W2044024574","https://openalex.org/W2003171342"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,93],"fixed-":[4],"and":[5,23,61,110],"low-dimensional,":[6],"perceptually":[7],"based":[8],"dynamic":[9,43],"sinusoidal":[10,28,35,44],"model":[11,72],"of":[12,27,67,84,113,125,137],"speech":[13,106],"referred":[14],"to":[15,39,104,120],"as":[16],"PDM":[17,109,131],"(Perceptual":[18],"Dynamic":[19],"Model).":[20],"To":[21],"decrease":[22],"fix":[24],"the":[25,33,52,55,64,82,85,90,140],"number":[26,124],"components":[29],"typically":[30],"used":[31],"in":[32,135],"standard":[34],"model,":[36],"we":[37],"propose":[38],"use":[40,121],"only":[41],"one":[42],"component":[45,96],"per":[46],"critical":[47,69],"band.":[48,70],"For":[49],"each":[50],"band,":[51],"sinusoid":[53],"with":[54,63,108],"maximum":[56],"spectral":[57],"amplitude":[58],"is":[59,73,97,102,132],"selected":[60],"associated":[62],"centre":[65],"frequency":[66],"that":[68,130],"The":[71,127],"expanded":[74],"at":[75,81,89],"low":[76],"frequencies":[77,92],"by":[78],"incorporating":[79],"sinusoids":[80],"boundaries":[83],"corresponding":[86],"bands":[87],"while":[88],"higher":[91],"modulated":[94],"noise":[95],"used.":[98],"A":[99],"listening":[100],"test":[101],"conducted":[103],"compare":[105],"reconstructed":[107],"state-of-the-art":[111],"models":[112,117],"speech,":[114],"where":[115],"all":[116],"are":[118],"constrained":[119],"an":[122],"equal":[123],"parameters.":[126],"results":[128],"show":[129],"clearly":[133],"preferred":[134],"terms":[136],"quality":[138],"over":[139],"other":[141],"systems.":[142]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}