{"id":"https://openalex.org/W3104580832","doi":"https://doi.org/10.1109/slt48900.2021.9383629","title":"Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis","display_name":"Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3104580832","doi":"https://doi.org/10.1109/slt48900.2021.9383629","mag":"3104580832"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.06465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072923563","display_name":"Chung-Ming Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chung-Ming Chien","raw_affiliation_strings":["National Taiwan University, Taiwan","National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["National Taiwan University, Taiwan","National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072923563"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.42331073,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66427251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"453"},"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":0.9977999925613403,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.9673354625701904},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8604026436805725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6683222055435181},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5922645330429077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5910853147506714},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5001747608184814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4654090702533722},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4626401960849762},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42567890882492065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4205835461616516},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4205256998538971},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12683826684951782},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.058109164237976074}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9673354625701904},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8604026436805725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6683222055435181},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5922645330429077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5910853147506714},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5001747608184814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4654090702533722},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4626401960849762},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42567890882492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205835461616516},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4205256998538971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12683826684951782},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.058109164237976074},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.06465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.06465","pdf_url":"https://arxiv.org/pdf/2011.06465","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":"doi:10.48550/arxiv.2011.06465","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.06465","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":"article"},{"id":"doi:10.17023/15fd-8c48","is_oa":true,"landing_page_url":"https://doi.org/10.17023/15fd-8c48","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3104580832","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.06465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.06465","pdf_url":"https://arxiv.org/pdf/2011.06465","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":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3104580832.pdf","grobid_xml":"https://content.openalex.org/works/W3104580832.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W349236604","https://openalex.org/W1563089615","https://openalex.org/W2107740512","https://openalex.org/W2396366106","https://openalex.org/W2550497374","https://openalex.org/W2563351168","https://openalex.org/W2747874407","https://openalex.org/W2752796333","https://openalex.org/W2795109282","https://openalex.org/W2885800352","https://openalex.org/W2904459034","https://openalex.org/W2945544731","https://openalex.org/W2963272440","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963568578","https://openalex.org/W2963799213","https://openalex.org/W2963927338","https://openalex.org/W2964121744","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2970730223","https://openalex.org/W2973190645","https://openalex.org/W2988217457","https://openalex.org/W3015440759","https://openalex.org/W3016021263","https://openalex.org/W3026741798","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W6631190155","https://openalex.org/W6633684334","https://openalex.org/W6712235671","https://openalex.org/W6731031554","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6755300632","https://openalex.org/W6762643587","https://openalex.org/W6763832098","https://openalex.org/W6765540686","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3151450932","https://openalex.org/W2347684782","https://openalex.org/W3048845410","https://openalex.org/W2168772993","https://openalex.org/W652196294","https://openalex.org/W3203313352","https://openalex.org/W2168759588","https://openalex.org/W2389811088","https://openalex.org/W2392752672","https://openalex.org/W2382060337","https://openalex.org/W1964101772","https://openalex.org/W1986255239","https://openalex.org/W2537421476","https://openalex.org/W2626979164","https://openalex.org/W2566926092","https://openalex.org/W2612504417","https://openalex.org/W2064571911","https://openalex.org/W2612157710","https://openalex.org/W2332464857","https://openalex.org/W2370805772"],"abstract_inverted_index":{"Prosody":[0],"modeling":[1],"is":[2,38],"an":[3],"essential":[4],"component":[5],"in":[6,60,81,89],"modern":[7],"text-to-speech":[8],"(TTS)":[9],"frameworks.":[10],"By":[11],"explicitly":[12],"providing":[13],"prosody":[14,34,66,73,87],"features":[15,67],"to":[16],"the":[17,20,45,62,71],"TTS":[18,49],"model,":[19],"style":[21],"of":[22,47,64,83],"synthesized":[23],"utterances":[24],"can":[25],"thus":[26],"be":[27],"controlled.":[28],"However,":[29],"predicting":[30],"natural":[31],"and":[32,55,86,92],"reasonable":[33],"at":[35],"inference":[36],"time":[37],"challenging.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"analyzed":[44],"behavior":[46],"non-autoregressive":[48],"models":[50],"under":[51],"different":[52],"prosody-modeling":[53],"settings":[54],"proposed":[56,76],"a":[57],"hierarchical":[58],"architecture,":[59],"which":[61],"prediction":[63],"phoneme-level":[65],"are":[68],"conditioned":[69],"on":[70],"word-level":[72],"features.":[74],"The":[75],"method":[77],"outperforms":[78],"other":[79],"competitors":[80],"terms":[82],"audio":[84],"quality":[85],"naturalness":[88],"our":[90],"objective":[91],"subjective":[93],"evaluation.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}