{"id":"https://openalex.org/W3047796745","doi":"https://doi.org/10.21437/interspeech.2020-2918","title":"Controllable Neural Prosody Synthesis","display_name":"Controllable Neural Prosody Synthesis","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3047796745","doi":"https://doi.org/10.21437/interspeech.2020-2918","mag":"3047796745"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2918","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.03388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102779961","display_name":"Max Morrison","orcid":"https://orcid.org/0000-0002-6082-5157"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max Morrison","raw_affiliation_strings":["Northwestern University, Evanston, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, United States","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Princeton University, Princeton, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, United States","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Salamon","raw_affiliation_strings":["New York University, New York, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University, New York, United States","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045694117","display_name":"Nicholas J. Bryan","orcid":"https://orcid.org/0000-0003-1469-7278"},"institutions":[{"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":["IL"],"is_corresponding":false,"raw_author_name":"Nicholas J. Bryan","raw_affiliation_strings":["Apple (Israel), Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple (Israel), Herzliya, Israel","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044614923","display_name":"Gautham J. Mysore","orcid":"https://orcid.org/0000-0003-0483-9252"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautham J. Mysore","raw_affiliation_strings":["Adobe Systems (United States), San Jose, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Systems (United States), San Jose, United States","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4437","last_page":"4441"},"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":0.9995999932289124,"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":0.9988999962806702,"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/prosody","display_name":"Prosody","score":0.9627323150634766},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8424204587936401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6737830638885498},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6171661615371704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6170987486839294},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5635864734649658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38538575172424316},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38535863161087036},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.071616530418396}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9627323150634766},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8424204587936401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737830638885498},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6171661615371704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6170987486839294},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5635864734649658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38538575172424316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38535863161087036},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.071616530418396},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2918","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.03388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03388","pdf_url":"https://arxiv.org/pdf/2008.03388","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3047796745","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.03388.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.03388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.03388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.03388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03388","pdf_url":"https://arxiv.org/pdf/2008.03388","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047796745.pdf","grobid_xml":"https://content.openalex.org/works/W3047796745.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1500192039","https://openalex.org/W1522301498","https://openalex.org/W2029434926","https://openalex.org/W2029996593","https://openalex.org/W2104917577","https://openalex.org/W2148228080","https://openalex.org/W2154280657","https://openalex.org/W2174424190","https://openalex.org/W2471520273","https://openalex.org/W2747914378","https://openalex.org/W2749651610","https://openalex.org/W2792995953","https://openalex.org/W2801493797","https://openalex.org/W2808476266","https://openalex.org/W2885800352","https://openalex.org/W2888855092","https://openalex.org/W2890983311","https://openalex.org/W2897548994","https://openalex.org/W2962866891","https://openalex.org/W2963175743","https://openalex.org/W2963341956","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2973013313","https://openalex.org/W2973115941","https://openalex.org/W2977311057","https://openalex.org/W2980282514","https://openalex.org/W2982602185","https://openalex.org/W2993118648","https://openalex.org/W2996573371","https://openalex.org/W3005492244"],"related_works":["https://openalex.org/W3097003111","https://openalex.org/W3048845410","https://openalex.org/W2964138190","https://openalex.org/W3101882441","https://openalex.org/W2981382721","https://openalex.org/W2067500459","https://openalex.org/W652196294","https://openalex.org/W3203313352","https://openalex.org/W3135547455","https://openalex.org/W2795109282","https://openalex.org/W2042667864","https://openalex.org/W1964101772","https://openalex.org/W2373820701","https://openalex.org/W2586711829","https://openalex.org/W1575559702","https://openalex.org/W3086296097","https://openalex.org/W3160844600","https://openalex.org/W2579204149","https://openalex.org/W3185312023","https://openalex.org/W3022876224"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1],"has":[2],"recently":[3],"seen":[4],"significant":[5],"improvements":[6],"in":[7],"fidelity,":[8],"driven":[9],"by":[10],"the":[11,86,109,133,137],"advent":[12],"of":[13,136],"neural":[14,17,61,101],"vocoders":[15],"and":[16,39,51,84,93,114],"prosody":[18,34,62,78,128],"generators.":[19],"However,":[20],"these":[21,55],"systems":[22],"lack":[23],"intuitive":[24],"user":[25,75,124],"controls":[26],"over":[27],"prosody,":[28],"making":[29],"them":[30],"unable":[31],"to":[32,76,103,107],"rectify":[33],"errors":[35],"(e.g.,":[36],"misplaced":[37],"emphases":[38],"contextually":[40],"inappropriate":[41],"emotions)":[42],"or":[43,67],"generate":[44],"prosodies":[45],"with":[46,57],"diverse":[47],"speaker":[48],"excitement":[49],"levels":[50],"emotions.":[52],"We":[53,96],"address":[54],"limitations":[56],"a":[58,65,74,99],"user-controllable,":[59],"context-aware":[60],"generator.":[63],"Given":[64],"real":[66],"synthesized":[68,110,138],"speech":[69,106],"recording,":[70],"our":[71,127],"model":[72,130],"allows":[73],"input":[77,91,105],"constraints":[79],"for":[80],"certain":[81],"time":[82,88],"frames":[83,89],"generates":[85],"remaining":[87],"from":[90],"text":[92],"contextual":[94],"prosody.":[95,111],"also":[97],"propose":[98],"pitch-shifting":[100],"vocoder":[102],"modify":[104],"match":[108],"Through":[112],"objective":[113],"subjective":[115],"evaluations":[116],"we":[117,120],"show":[118],"that":[119],"can":[121],"successfully":[122],"incorporate":[123],"control":[125],"into":[126],"generation":[129],"without":[131],"sacrificing":[132],"overall":[134],"naturalness":[135],"speech.":[139]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}