{"id":"https://openalex.org/W3202098869","doi":"https://doi.org/10.1109/icassp43922.2022.9746253","title":"Hierarchical Prosody Modeling and Control in Non-Autoregressive Parallel Neural TTS","display_name":"Hierarchical Prosody Modeling and Control in Non-Autoregressive Parallel Neural TTS","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3202098869","doi":"https://doi.org/10.1109/icassp43922.2022.9746253","mag":"3202098869"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746253","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005526135","display_name":"Jiangchuan Li","orcid":"https://orcid.org/0000-0002-6489-4766"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiangchuan Li","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048838330","display_name":"Shreyas Seshadri","orcid":"https://orcid.org/0000-0003-1731-3129"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shreyas Seshadri","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":2.699,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91671659,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7587","last_page":"7591"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9979000091552734,"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":0.7708398103713989},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7436697483062744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7109570503234863},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.68780118227005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6566748023033142},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5091521143913269},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5076109170913696},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4954797029495239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41327735781669617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1291605532169342},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0719681978225708}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7708398103713989},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7436697483062744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109570503234863},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.68780118227005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6566748023033142},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5091521143913269},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5076109170913696},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4954797029495239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41327735781669617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1291605532169342},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0719681978225708},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746253","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2184310502","https://openalex.org/W2513112113","https://openalex.org/W2519091744","https://openalex.org/W2626778328","https://openalex.org/W2745387029","https://openalex.org/W2747681982","https://openalex.org/W2766812927","https://openalex.org/W2788851830","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2897548994","https://openalex.org/W2904459034","https://openalex.org/W2945544731","https://openalex.org/W2946200149","https://openalex.org/W2952269766","https://openalex.org/W2963272440","https://openalex.org/W2963927338","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2972484110","https://openalex.org/W2974194285","https://openalex.org/W3016021263","https://openalex.org/W3027876491","https://openalex.org/W3033411150","https://openalex.org/W3093733783","https://openalex.org/W3097892637","https://openalex.org/W3100400819","https://openalex.org/W3101882441","https://openalex.org/W3104580832","https://openalex.org/W3125687907","https://openalex.org/W3130016944","https://openalex.org/W3144667183","https://openalex.org/W3151450932","https://openalex.org/W3161296985","https://openalex.org/W3196964833","https://openalex.org/W3198712562","https://openalex.org/W3199015956","https://openalex.org/W4210684870","https://openalex.org/W4287761884","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745697700","https://openalex.org/W6746700228","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6763832098","https://openalex.org/W6764068927","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6784809985"],"related_works":["https://openalex.org/W258725851","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"Neural":[0],"text-to-speech":[1],"(TTS)":[2],"synthesis":[3],"can":[4,108],"generate":[5,114],"speech":[6,16,76],"that":[7,91],"is":[8],"indistinguishable":[9],"from":[10],"natural":[11],"speech.":[12],"However,":[13],"the":[14,19,24,37,41,52,133],"synthetic":[15],"often":[17],"represents":[18],"average":[20],"prosodic":[21,31,112],"style":[22],"of":[23,27,118],"database":[25],"instead":[26],"having":[28],"more":[29],"versatile":[30],"variation.":[32],"Moreover,":[33],"many":[34],"models":[35],"lack":[36],"ability":[38],"to":[39,78,132],"control":[40,110],"output":[42],"prosody,":[43],"which":[44],"does":[45],"not":[46],"allow":[47],"for":[48,51],"different":[49],"styles":[50],"same":[53],"text":[54],"input.":[55],"In":[56],"this":[57],"work,":[58],"we":[59],"train":[60],"a":[61,80,92,115],"non-autoregressive":[62,93],"parallel":[63],"neural":[64],"TTS":[65,94],"front-end":[66],"model":[67,95],"hierarchically":[68,96],"conditioned":[69,97],"on":[70,98],"both":[71],"coarse":[72],"and":[73,86,105,121],"fine-grained":[74],"acoustic":[75],"features":[77],"learn":[79],"latent":[81],"prosody":[82],"space":[83],"with":[84],"intuitive":[85],"meaningful":[87],"dimensions.":[88],"Experiments":[89],"show":[90],"utterance-wise":[99],"pitch,":[100],"pitch":[101],"range,":[102],"duration,":[103],"energy,":[104],"spectral":[106],"tilt":[107],"effectively":[109],"each":[111],"dimension,":[113],"wide":[116],"variety":[117],"speaking":[119],"styles,":[120],"provide":[122],"word-wise":[123],"emphasis":[124],"control,":[125],"while":[126],"maintaining":[127],"equal":[128],"or":[129],"better":[130],"quality":[131],"baseline":[134],"model.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}