{"id":"https://openalex.org/W3016021263","doi":"https://doi.org/10.1109/icassp40776.2020.9053520","title":"Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis","display_name":"Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016021263","doi":"https://doi.org/10.1109/icassp40776.2020.9053520","mag":"3016021263"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5077772423","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0002-5886-056X"},"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":true,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["University of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"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":"Yu Zhang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"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":"Ron J. Weiss","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101989491","display_name":"Yuan Cao","orcid":"https://orcid.org/0000-0002-2495-4701"},"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":"Yuan Cao","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"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":"Heiga Zen","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"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":"Yonghui Wu","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5077772423"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":10.0746,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.98543627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.8968414664268494},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.812201738357544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7084235548973083},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5775742530822754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.563879668712616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5466381907463074},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.5340444445610046},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4876750707626343},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.452495276927948},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14328879117965698},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13719218969345093}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8968414664268494},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.812201738357544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084235548973083},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5775742530822754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.563879668712616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5466381907463074},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.5340444445610046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4876750707626343},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.452495276927948},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14328879117965698},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13719218969345093},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W2069859485","https://openalex.org/W2091425152","https://openalex.org/W2107740512","https://openalex.org/W2130942839","https://openalex.org/W2140574335","https://openalex.org/W2559823555","https://openalex.org/W2621357189","https://openalex.org/W2753738274","https://openalex.org/W2758785877","https://openalex.org/W2766812927","https://openalex.org/W2785519580","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2805530975","https://openalex.org/W2884607399","https://openalex.org/W2889028433","https://openalex.org/W2901997113","https://openalex.org/W2903538854","https://openalex.org/W2904459034","https://openalex.org/W2907262790","https://openalex.org/W2917688842","https://openalex.org/W2948238043","https://openalex.org/W2950662112","https://openalex.org/W2962689740","https://openalex.org/W2962690557","https://openalex.org/W2962691331","https://openalex.org/W2963047245","https://openalex.org/W2963104724","https://openalex.org/W2963226019","https://openalex.org/W2963264829","https://openalex.org/W2963272440","https://openalex.org/W2963366547","https://openalex.org/W2963403868","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963618559","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964204277","https://openalex.org/W2964243274","https://openalex.org/W2971074500","https://openalex.org/W2972359262","https://openalex.org/W2977311057","https://openalex.org/W2981870653","https://openalex.org/W2996573371","https://openalex.org/W4289383906","https://openalex.org/W4293411471","https://openalex.org/W4293849739","https://openalex.org/W4295112158","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W6675938391","https://openalex.org/W6677973343","https://openalex.org/W6679436768","https://openalex.org/W6680537413","https://openalex.org/W6718140377","https://openalex.org/W6730405185","https://openalex.org/W6738536549","https://openalex.org/W6739901393","https://openalex.org/W6744627333","https://openalex.org/W6745117592","https://openalex.org/W6745687250","https://openalex.org/W6745697700","https://openalex.org/W6748223763","https://openalex.org/W6750489868","https://openalex.org/W6751810238","https://openalex.org/W6755300632","https://openalex.org/W6756197946","https://openalex.org/W6756663807","https://openalex.org/W7075712485"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4311431240","https://openalex.org/W4312407344","https://openalex.org/W4384115502","https://openalex.org/W4287870311","https://openalex.org/W3005492244"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,45],"hierarchical,":[4],"fine-grained":[5],"and":[6,84,91],"interpretable":[7],"latent":[8,42,105],"variable":[9],"model":[10,67],"for":[11],"prosody":[12,25,74,86],"based":[13],"on":[14,31],"the":[15,60,66,80,98,101,104],"Tacotron":[16],"2":[17],"text-to-speech":[18],"model.":[19],"It":[20],"achieves":[21],"multi-resolution":[22],"modeling":[23],"of":[24,55,73,103],"by":[26],"conditioning":[27,39],"finer":[28],"level":[29,33],"representations":[30],"coarser":[32],"ones.":[34],"Additionally,":[35],"it":[36],"imposes":[37],"hierarchical":[38],"across":[40],"all":[41],"dimensions":[43],"using":[44],"conditional":[46],"variational":[47],"auto-encoder":[48],"(VAE)":[49],"with":[50,79],"an":[51],"auto-regressive":[52],"structure.":[53],"Evaluation":[54],"reconstruction":[56],"performance":[57],"illustrates":[58],"that":[59],"new":[61],"structure":[62],"does":[63],"not":[64],"degrade":[65],"while":[68],"allowing":[69],"better":[70],"interpretability.":[71],"Interpretations":[72],"attributes":[75],"are":[76,94],"provided":[77],"together":[78],"comparison":[81],"between":[82],"word-level":[83],"phone-level":[85],"representations.":[87],"Moreover,":[88],"both":[89],"qualitative":[90],"quantitative":[92],"evaluations":[93],"used":[95],"to":[96],"demonstrate":[97],"improvement":[99],"in":[100],"disentanglement":[102],"dimensions.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}