{"id":"https://openalex.org/W2567070270","doi":"https://doi.org/10.1109/eusipco.2016.7760663","title":"Acoustic feature prediction from semantic features for expressive speech using deep neural networks","display_name":"Acoustic feature prediction from semantic features for expressive speech using deep neural networks","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2567070270","doi":"https://doi.org/10.1109/eusipco.2016.7760663","mag":"2567070270"},"language":"en","primary_location":{"id":"doi:10.1109/eusipco.2016.7760663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2016.7760663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 24th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/117303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079323004","display_name":"Igor Jauk","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Igor Jauk","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101557983","display_name":"Santiago Pascual","orcid":"https://orcid.org/0000-0002-8365-7387"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"2320","last_page":"2324"},"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":0.9997000098228455,"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":0.9991999864578247,"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":0.8279825448989868},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.720539927482605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6354891061782837},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6040367484092712},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5609618425369263},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5601018071174622},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5382352471351624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5150101184844971},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5055584907531738},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.44085147976875305},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4347441494464874},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4211844503879547},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40865814685821533},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3842359185218811},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.32917267084121704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279825448989868},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.720539927482605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6354891061782837},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6040367484092712},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5609618425369263},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5601018071174622},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5382352471351624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5150101184844971},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5055584907531738},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.44085147976875305},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4347441494464874},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4211844503879547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40865814685821533},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3842359185218811},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32917267084121704},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/eusipco.2016.7760663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2016.7760663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 24th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:recercat.cat:2072/308590","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/117303","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/308590","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/117303","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320333121","display_name":"University of Texas at El Paso","ror":"https://ror.org/04d5vba33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W204967857","https://openalex.org/W1524333225","https://openalex.org/W1569087642","https://openalex.org/W1614298861","https://openalex.org/W2018493666","https://openalex.org/W2041823554","https://openalex.org/W2059721297","https://openalex.org/W2079521622","https://openalex.org/W2083543775","https://openalex.org/W2095705004","https://openalex.org/W2099062766","https://openalex.org/W2121415728","https://openalex.org/W2123864036","https://openalex.org/W2142349102","https://openalex.org/W2150341604","https://openalex.org/W2150769028","https://openalex.org/W2156146072","https://openalex.org/W2169295472","https://openalex.org/W2282712048","https://openalex.org/W2283817422","https://openalex.org/W2294232014","https://openalex.org/W2295406225","https://openalex.org/W2338806053","https://openalex.org/W4205947740","https://openalex.org/W4390911599","https://openalex.org/W6608248944","https://openalex.org/W6631362777","https://openalex.org/W6633893584","https://openalex.org/W6636510571","https://openalex.org/W6674330103","https://openalex.org/W6695580952","https://openalex.org/W6695760510","https://openalex.org/W6703597077"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2766569399","https://openalex.org/W2156831951","https://openalex.org/W1992816027"],"abstract_inverted_index":{"The":[0,45,63,116],"goal":[1],"of":[2,10,21,74],"the":[3,31,80,97,114,122,129],"study":[4],"is":[5,65,77,118],"to":[6,56],"predict":[7],"acoustic":[8,51,58,75,108],"features":[9,59,76,110],"expressive":[11],"speech":[12,43],"from":[13,60,79],"semantic":[14,69,98,106],"vector":[15,70],"space":[16],"representations.":[17],"Though":[18],"a":[19,68,102],"lot":[20],"successful":[22],"work":[23],"was":[24],"invested":[25],"in":[26,67],"expressiveness":[27],"analysis":[28,47,126],"and":[29,54,88,101,107,141,147],"prediction,":[30],"results":[32],"often":[33],"involve":[34],"manual":[35],"labeling,":[36],"or":[37,136],"indirect":[38],"prediction":[39,53,117,130],"evaluation":[40],"such":[41],"as":[42],"synthesis.":[44],"proposed":[46],"aims":[48],"at":[49],"direct":[50],"feature":[52],"comparison":[55],"original":[57],"an":[61],"audiobook.":[62],"audiobook":[64],"mapped":[66],"space.":[71],"A":[72,124],"set":[73],"extracted":[78],"same":[81],"utterances,":[82],"involving":[83],"iVectors":[84],"trained":[85,95],"on":[86],"MFCC":[87],"F0":[89],"basis.":[90],"Two":[91],"regression":[92],"models":[93],"are":[94,111],"with":[96,138],"coordinates,":[99],"DNNs":[100],"baseline":[103],"CART.":[104],"Later,":[105],"context":[109],"combined":[112],"for":[113,133,143],"prediction.":[115],"achieved":[119],"successfully":[120],"using":[121],"DNNs.":[123],"closer":[125],"shows":[127],"that":[128],"works":[131],"best":[132],"larger":[134],"utterances":[135,137,146],"specific":[139],"contexts,":[140],"worst":[142],"general":[144],"short":[145],"proper":[148],"names.":[149]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}