{"id":"https://openalex.org/W2938833595","doi":"https://doi.org/10.1109/icassp.2019.8683865","title":"Sequence-to-sequence Modelling of F0 for Speech Emotion Conversion","display_name":"Sequence-to-sequence Modelling of F0 for Speech Emotion Conversion","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938833595","doi":"https://doi.org/10.1109/icassp.2019.8683865","mag":"2938833595"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029755681","display_name":"Carl Robinson","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Carl Robinson","raw_affiliation_strings":["IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042745853","display_name":"Nicolas Obin","orcid":"https://orcid.org/0000-0002-5236-5306"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Obin","raw_affiliation_strings":["IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065828059","display_name":"Axel R\u00f6ebel","orcid":"https://orcid.org/0000-0001-6136-4391"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Axel Roebel","raw_affiliation_strings":["IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRCAM, CNRS, Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9044,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.94835943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6830","last_page":"6834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9952999949455261,"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/T12031","display_name":"Speech and dialogue systems","score":0.9868000149726868,"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/speech-recognition","display_name":"Speech recognition","score":0.7755222916603088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147719264030457},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.616866409778595},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.565766453742981},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5469565391540527},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5138547420501709},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.502666711807251},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4628737270832062},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.4601687788963318},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4585762321949005},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4220472574234009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34681951999664307},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2028902769088745}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7755222916603088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147719264030457},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.616866409778595},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.565766453742981},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5469565391540527},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5138547420501709},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.502666711807251},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4628737270832062},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.4601687788963318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4585762321949005},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4220472574234009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34681951999664307},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2028902769088745},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W15106243","https://openalex.org/W63438600","https://openalex.org/W113106864","https://openalex.org/W1570629387","https://openalex.org/W1576227399","https://openalex.org/W2018338387","https://openalex.org/W2106421426","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2158504378","https://openalex.org/W2184310502","https://openalex.org/W2294797155","https://openalex.org/W2407110532","https://openalex.org/W2513051195","https://openalex.org/W2517513811","https://openalex.org/W2519091744","https://openalex.org/W2604184139","https://openalex.org/W2605141709","https://openalex.org/W2613654124","https://openalex.org/W2674088828","https://openalex.org/W2740504963","https://openalex.org/W2746192915","https://openalex.org/W2747914378","https://openalex.org/W2805307277","https://openalex.org/W2808514527","https://openalex.org/W2886195082","https://openalex.org/W2949382160","https://openalex.org/W2964308564","https://openalex.org/W3142087749","https://openalex.org/W6600618385","https://openalex.org/W6602504493","https://openalex.org/W6604530167","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6683488333","https://openalex.org/W6696843773","https://openalex.org/W6713858911","https://openalex.org/W6736356763","https://openalex.org/W6751998403"],"related_works":["https://openalex.org/W2535580602","https://openalex.org/W2088933974","https://openalex.org/W1966171935","https://openalex.org/W2387192134","https://openalex.org/W1600688796","https://openalex.org/W1607387412","https://openalex.org/W2150511655","https://openalex.org/W2535215250","https://openalex.org/W2142042197","https://openalex.org/W2164147372"],"abstract_inverted_index":{"Voice":[0],"interfaces":[1],"are":[2],"becoming":[3],"wildly":[4],"popular":[5],"and":[6,14,40],"driving":[7],"demand":[8],"for":[9],"more":[10],"advanced":[11],"speech":[12,56,60,106],"synthesis":[13],"voice":[15,46,85,123],"transformation":[16],"systems.":[17],"Current":[18],"text-to-speech":[19],"methods":[20],"produce":[21,121],"realistic":[22],"sounding":[23],"voices,":[24],"but":[25],"they":[26],"lack":[27],"the":[28,35,38,41,68,80,103,113,116,129,132,135,138],"emotional":[29],"expressivity":[30],"that":[31],"listeners":[32,110],"expect,":[33],"given":[34],"context":[36],"of":[37,70,82,95,105,115,134],"interaction":[39],"phrase":[42,139],"being":[43],"spoken.":[44],"Emotional":[45],"conversion":[47],"is":[48],"a":[49,72,83],"research":[50,66],"domain":[51],"concerned":[52],"with":[53,91],"generating":[54],"expressive":[55,89],"from":[57,86],"neutral":[58,87],"synthesised":[59],"or":[61],"natural":[62],"human":[63,84],"voice.":[64],"This":[65],"investigated":[67],"effectiveness":[69,114],"using":[71],"sequence-to-sequence":[73,118],"(seq2seq)":[74],"encoder-decoder":[75],"based":[76],"model":[77,130],"to":[78,88,120],"transform":[79],"intonation":[81],"speech,":[90],"some":[92],"preliminary":[93],"introduction":[94],"linguistic":[96],"conditioning.":[97],"A":[98],"subjective":[99],"experiment":[100],"conducted":[101],"on":[102,131],"task":[104],"emotion":[107,124],"recognition":[108,142],"by":[109],"successfully":[111],"demonstrated":[112],"proposed":[117],"models":[119],"convincing":[122],"transformations.":[125],"In":[126],"particular,":[127],"conditioning":[128],"position":[133],"syllable":[136],"in":[137],"significantly":[140],"improved":[141],"rates.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}