{"id":"https://openalex.org/W4392903668","doi":"https://doi.org/10.1109/icassp48485.2024.10446859","title":"Controllable Prosody Generation with Partial Inputs","display_name":"Controllable Prosody Generation with Partial Inputs","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903668","doi":"https://doi.org/10.1109/icassp48485.2024.10446859"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076766517","display_name":"Dan Andrei Iliescu","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dan Andrei Iliescu","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024033876","display_name":"Devang S Ram Mohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devang S Ram Mohan","raw_affiliation_strings":["Papercup Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038517086","display_name":"Tian Huey Teh","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Huey Teh","raw_affiliation_strings":["Google Deepmind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Deepmind","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041839891","display_name":"Zack Hodari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zack Hodari","raw_affiliation_strings":["Papercup Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Papercup Technologies","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7112,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65939051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11916","last_page":"11920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9979000091552734,"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/prosody","display_name":"Prosody","score":0.7963579297065735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7922464609146118},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.677986204624176},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6381625533103943},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6137241125106812},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5704479217529297},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5321715474128723},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4879104793071747},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45549094676971436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44746994972229004}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7963579297065735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922464609146118},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.677986204624176},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6381625533103943},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6137241125106812},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5704479217529297},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5321715474128723},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4879104793071747},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45549094676971436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44746994972229004},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W658512522","https://openalex.org/W1741471588","https://openalex.org/W2069859485","https://openalex.org/W2122364000","https://openalex.org/W2188365844","https://openalex.org/W2331655103","https://openalex.org/W2752796333","https://openalex.org/W2785934082","https://openalex.org/W2949973225","https://openalex.org/W2962974533","https://openalex.org/W2964138190","https://openalex.org/W2973013313","https://openalex.org/W2992838650","https://openalex.org/W3105938520","https://openalex.org/W3170320568","https://openalex.org/W3192495122","https://openalex.org/W3196843885","https://openalex.org/W4224035735","https://openalex.org/W4296068407","https://openalex.org/W4298580827","https://openalex.org/W6687045409","https://openalex.org/W6745117592","https://openalex.org/W6747701563","https://openalex.org/W6748409065","https://openalex.org/W6757140150","https://openalex.org/W6773169357","https://openalex.org/W6809885388","https://openalex.org/W6852305316","https://openalex.org/W6940163724"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W4365211920","https://openalex.org/W3149582125","https://openalex.org/W3014948380","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294"],"abstract_inverted_index":{"We":[0,60,77],"address":[1],"the":[2,11,33,47,53,57,111,114],"problem":[3],"of":[4,13,87,101,113,119],"human-in-the-loop":[5,89],"control":[6,90],"for":[7],"generating":[8],"prosody":[9,17],"in":[10,117],"context":[12],"text-to-speech":[14],"synthesis.":[15],"Controlling":[16],"is":[18,65],"challenging":[19],"because":[20],"existing":[21],"generative":[22,54],"models":[23],"lack":[24],"an":[25],"efficient":[26],"interface":[27],"through":[28],"which":[29],"users":[30,108],"can":[31],"modify":[32],"output":[34,74,115],"quickly":[35],"and":[36,52,73,93],"precisely.":[37],"To":[38],"solve":[39],"this,":[40],"we":[41],"introduce":[42],"a":[43,62,88,97],"novel":[44],"framework":[45],"whereby":[46],"user":[48],"provides":[49],"partial":[50,70],"inputs":[51],"model":[55,63,82,106],"generates":[56],"missing":[58],"features.":[59],"propose":[61],"that":[64,80],"specifically":[66],"designed":[67],"to":[68,109],"encode":[69],"prosodic":[71],"features":[72],"complete":[75],"audio.":[76],"show":[78],"empirically":[79],"our":[81,105],"displays":[83],"two":[84],"essential":[85],"qualities":[86],"mechanism:":[91],"efficiency":[92],"robustness.":[94],"With":[95],"even":[96],"very":[98],"small":[99],"number":[100],"input":[102],"values":[103],"(~4),":[104],"enables":[107],"improve":[110],"quality":[112],"significantly":[116],"terms":[118],"listener":[120],"preference":[121],"(4:1).":[122]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}