{"id":"https://openalex.org/W2109915598","doi":"https://doi.org/10.1109/icassp.2012.6288919","title":"Gaussian process dynamical models for nonparametric speech representation and synthesis","display_name":"Gaussian process dynamical models for nonparametric speech representation and synthesis","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2109915598","doi":"https://doi.org/10.1109/icassp.2012.6288919","mag":"2109915598"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288919","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":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-66403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["School of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020402037","display_name":"Marcus Frean","orcid":"https://orcid.org/0000-0001-5840-8760"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Marcus R. Frean","raw_affiliation_strings":["School of Engineering and Computer Science, Victoria University of Wellington, New Zealand"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Computer Science, Victoria University of Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087492771","display_name":"W. Bastiaan Kleijn","orcid":"https://orcid.org/0000-0002-1973-3920"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["NZ","SE"],"is_corresponding":false,"raw_author_name":"W. Bastiaan Kleijn","raw_affiliation_strings":["School of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, Sweden","School of Engineering and Computer Science, Victoria University of Wellington, New Zealand"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"School of Engineering and Computer Science, Victoria University of Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091432739"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":6.8504,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96813381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"4505","last_page":"4508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9976000189781189,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9976000189781189,"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":0.9904000163078308,"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":0.9796000123023987,"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/computer-science","display_name":"Computer science","score":0.712460994720459},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6384824514389038},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.6239836812019348},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.619577169418335},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.543246865272522},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5326594710350037},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5322142839431763},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5175356268882751},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5029780268669128},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45996055006980896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42699721455574036},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4148465394973755},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3566090166568756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2308727204799652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.712460994720459},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6384824514389038},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.6239836812019348},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.619577169418335},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.543246865272522},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5326594710350037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5322142839431763},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5175356268882751},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5029780268669128},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45996055006980896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42699721455574036},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4148465394973755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3566090166568756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2308727204799652},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288919","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:DiVA.org:kth-66403","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-66403","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-66403","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-66403","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"","raw_type":"Conference paper"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W79929747","https://openalex.org/W175280642","https://openalex.org/W1746819321","https://openalex.org/W1979449467","https://openalex.org/W2124609748","https://openalex.org/W2124765650","https://openalex.org/W2125838338","https://openalex.org/W2143029619","https://openalex.org/W2152205330","https://openalex.org/W2154920538","https://openalex.org/W2166063021","https://openalex.org/W3112742061","https://openalex.org/W4211049957","https://openalex.org/W6607096815"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"We":[0,81],"propose":[1],"Gaussian":[2,68],"process":[3],"dynamical":[4],"models":[5,14,71],"(GPDMs)":[6],"as":[7,46,53],"a":[8,57],"new,":[9],"nonparametric":[10],"paradigm":[11],"in":[12,49,56],"acoustic":[13],"of":[15,101,116],"speech.":[16],"These":[17],"use":[18],"multidimensional,":[19],"continuous":[20],"state-spaces":[21],"to":[22,37,93],"overcome":[23],"familiar":[24],"issues":[25],"with":[26],"discrete-state,":[27],"HMM-based":[28],"speech":[29,94,103,118],"models.":[30],"The":[31],"added":[32],"dimensions":[33],"allow":[34],"the":[35,70],"state":[36],"represent":[38],"and":[39,85,89],"describe":[40,86],"more":[41],"than":[42,52,104],"just":[43],"temporal":[44],"structure":[45],"systematic":[47],"differences":[48],"mean,":[50],"rather":[51],"mere":[54],"correlations":[55],"residual":[58],"(which":[59],"dynamic":[60],"features":[61],"or":[62,75],"AR-HMMs":[63],"do).":[64],"Being":[65],"based":[66],"on":[67,78],"processes,":[69],"avoid":[72],"restrictive":[73],"parametric":[74],"linearity":[76],"assumptions":[77],"signal":[79],"structure.":[80,119],"outline":[82],"GPDM":[83],"theory,":[84],"model":[87],"setup":[88],"initialization":[90],"schemes":[91],"relevant":[92],"applications.":[95],"Experiments":[96],"demonstrate":[97],"subjectively":[98],"better":[99],"quality":[100],"synthesized":[102],"from":[105],"comparable":[106],"HMMs.":[107],"In":[108],"addition,":[109],"there":[110],"is":[111],"evidence":[112],"for":[113],"unsupervised":[114],"discovery":[115],"salient":[117]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}