{"id":"https://openalex.org/W1613141907","doi":"https://doi.org/10.1109/icassp.2015.7178815","title":"Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE","display_name":"Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1613141907","doi":"https://doi.org/10.1109/icassp.2015.7178815","mag":"1613141907"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/eba288ec-f201-47b3-a373-83f0473af8d1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063890110","display_name":"Benigno Ur\u00eda","orcid":null},"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":"Benigno Uria","raw_affiliation_strings":["Institute for Adaptive and Neural Computation, University of Edinburgh, U.K","[Institute for Adaptive and Neural Computation, University of Edinburgh, U.K.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Adaptive and Neural Computation, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Institute for Adaptive and Neural Computation, University of Edinburgh, U.K.]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106707885","display_name":"Iain Murray","orcid":"https://orcid.org/0000-0002-6506-0472"},"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":"Iain Murray","raw_affiliation_strings":["Institute for Adaptive and Neural Computation, University of Edinburgh, U.K","[Institute for Adaptive and Neural Computation, University of Edinburgh, U.K.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Adaptive and Neural Computation, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Institute for Adaptive and Neural Computation, University of Edinburgh, U.K.]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"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":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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 for Speech Technology Research, University of Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103410518","display_name":"John S. Bridle","orcid":null},"institutions":[{"id":"https://openalex.org/I114203471","display_name":"University of Gloucestershire","ror":"https://ror.org/00wygct11","country_code":"GB","type":"education","lineage":["https://openalex.org/I114203471"]},{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"John Bridle","raw_affiliation_strings":["Apple Siri, Gloucestershire, U.K","[Apple Siri, Gloucestershire, U.K.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Siri, Gloucestershire, U.K","institution_ids":["https://openalex.org/I114203471"]},{"raw_affiliation_string":"[Apple Siri, Gloucestershire, U.K.]","institution_ids":["https://openalex.org/I1311269955"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"4465","last_page":"4469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.7422372698783875},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.696564793586731},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6546955108642578},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6367952227592468},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6245390772819519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6181930899620056},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5863611698150635},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5391502976417542},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4838787317276001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46619361639022827},{"id":"https://openalex.org/keywords/probabilistic-neural-network","display_name":"Probabilistic neural network","score":0.45656758546829224},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.44199898838996887},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4254765510559082},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.35659611225128174},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33726876974105835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3259583115577698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422372698783875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.696564793586731},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6546955108642578},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6367952227592468},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6245390772819519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6181930899620056},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5863611698150635},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5391502976417542},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4838787317276001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46619361639022827},{"id":"https://openalex.org/C134342201","wikidata":"https://www.wikidata.org/wiki/Q7246859","display_name":"Probabilistic neural network","level":4,"score":0.45656758546829224},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.44199898838996887},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4254765510559082},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.35659611225128174},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33726876974105835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3259583115577698},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2015.7178815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.1174","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.1174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.benignouria.com/en/research/papers/Uria2015.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/eba288ec-f201-47b3-a373-83f0473af8d1","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eba288ec-f201-47b3-a373-83f0473af8d1","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":"Uria, B, Murray, I, Renals, S, Valentini-Botinhao, C & Bridle, J 2015, Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE. in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on . pp. 4465-4469.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/eba288ec-f201-47b3-a373-83f0473af8d1","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/eba288ec-f201-47b3-a373-83f0473af8d1","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":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/eba288ec-f201-47b3-a373-83f0473af8d1","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eba288ec-f201-47b3-a373-83f0473af8d1","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":"Uria, B, Murray, I, Renals, S, Valentini-Botinhao, C & Bridle, J 2015, Modelling acoustic feature dependencies with artificial neural networks: Trajectory-RNADE. in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on . pp. 4465-4469.","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W183625566","https://openalex.org/W1514737389","https://openalex.org/W1554663460","https://openalex.org/W1579853615","https://openalex.org/W1665214252","https://openalex.org/W1979449467","https://openalex.org/W1990505856","https://openalex.org/W2000200144","https://openalex.org/W2000513720","https://openalex.org/W2024083195","https://openalex.org/W2024228246","https://openalex.org/W2027905573","https://openalex.org/W2049686551","https://openalex.org/W2102003408","https://openalex.org/W2104066451","https://openalex.org/W2106554350","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2135181320","https://openalex.org/W2140574335","https://openalex.org/W2143029619","https://openalex.org/W2154920538","https://openalex.org/W2163010125","https://openalex.org/W2170111110","https://openalex.org/W2188827208","https://openalex.org/W2406017614","https://openalex.org/W2952295562","https://openalex.org/W3140795192","https://openalex.org/W6634817459","https://openalex.org/W6637242042","https://openalex.org/W6680498451","https://openalex.org/W6680537413","https://openalex.org/W6681422213","https://openalex.org/W6684870364","https://openalex.org/W6687241212","https://openalex.org/W6714191056"],"related_works":["https://openalex.org/W1595652908","https://openalex.org/W2375446027","https://openalex.org/W2067837718","https://openalex.org/W2179098615","https://openalex.org/W2089093251","https://openalex.org/W38478948","https://openalex.org/W4385506173","https://openalex.org/W4294967761","https://openalex.org/W2139532495","https://openalex.org/W2950022897"],"abstract_inverted_index":{"Given":[0],"a":[1,5,78],"transcription,":[2],"sampling":[3],"from":[4,22],"good":[6],"model":[7,82],"of":[8,17,83],"acoustic":[9,46,70,84],"feature":[10],"trajectories":[11],"should":[12],"result":[13,28],"in":[14,29,53,66],"plausible":[15],"realizations":[16],"an":[18],"utterance.":[19],"However,":[20],"samples":[21],"current":[23],"probabilistic":[24,79],"speech":[25],"synthesis":[26],"systems":[27],"low":[30],"quality":[31,58],"synthetic":[32,59],"speech.":[33,60],"Henter":[34],"et":[35],"al.":[36],"have":[37],"demonstrated":[38],"the":[39,43,50],"need":[40],"to":[41,55,89],"capture":[42,90],"dependencies":[44,62],"between":[45],"features":[47],"conditioned":[48],"on":[49],"phonetic":[51],"labels":[52],"order":[54],"obtain":[56],"high":[57],"These":[61],"are":[63],"often":[64],"ignored":[65],"neural":[67,80],"network":[68,81],"based":[69],"models.":[71],"We":[72],"tackle":[73],"this":[74],"deficiency":[75],"by":[76],"introducing":[77],"trajectories,":[85],"trajectory":[86],"RNADE,":[87],"able":[88],"these":[91],"dependencies.":[92]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}