{"id":"https://openalex.org/W3134835907","doi":null,"title":"Mixture Density Network for Phone-Level Prosody Modelling in Speech Synthesis.","display_name":"Mixture Density Network for Phone-Level Prosody Modelling in Speech Synthesis.","publication_year":2021,"publication_date":"2021-02-01","ids":{"openalex":"https://openalex.org/W3134835907","mag":"3134835907"},"language":"en","primary_location":{"id":"mag:3134835907","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.00851","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2102.00851","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847","observed_orcids":["https://orcid.org/0000-0001-5329-0847"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5329-0847","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826","observed_orcids":["https://orcid.org/0000-0002-7102-9826"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mixture-density-networks","display_name":"mixture density networks","score":0.8109999895095825},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.8939999938011169},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.9909999966621399},{"id":"https://openalex.org/keywords/synthetic-speech-naturalness","display_name":"synthetic speech naturalness","score":0.8730000257492065},{"id":"https://openalex.org/keywords/ljspeech","display_name":"LJSpeech","score":0.859000027179718}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9336503744125366},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9274677038192749},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7935749888420105},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6689226627349854},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6332215666770935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6168699860572815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.580361545085907},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5529940128326416},{"id":"https://openalex.org/C2777500614","wikidata":"https://www.wikidata.org/wiki/Q738621","display_name":"Landline","level":3,"score":0.5429711937904358},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5030834078788757},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5006048679351807},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.48630771040916443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38714849948883057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33898985385894775},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11409294605255127},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06947061419487},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3134835907","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.00851","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:3134835907","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.00851","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W142684478","https://openalex.org/W1494198834","https://openalex.org/W1579853615","https://openalex.org/W1990505856","https://openalex.org/W2002342963","https://openalex.org/W2100969003","https://openalex.org/W2107860279","https://openalex.org/W2396366106","https://openalex.org/W2519091744","https://openalex.org/W2595110011","https://openalex.org/W2626778328","https://openalex.org/W2794490148","https://openalex.org/W2892140764","https://openalex.org/W2903739847","https://openalex.org/W2954099406","https://openalex.org/W2962691331","https://openalex.org/W2963609956","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/W3004823919","https://openalex.org/W3016021263","https://openalex.org/W3033411150","https://openalex.org/W3104580832"],"related_works":["https://openalex.org/W3197216873","https://openalex.org/W3164064632","https://openalex.org/W3216941316","https://openalex.org/W2482055902","https://openalex.org/W7015462037","https://openalex.org/W3203313352","https://openalex.org/W949867863","https://openalex.org/W96472724","https://openalex.org/W7002424147","https://openalex.org/W7099905863"],"abstract_inverted_index":{"Recent":[0],"researches":[1],"on":[2,45,62,123],"both":[3],"utterance-level":[4],"and":[5,14],"phone-level":[6,46,73],"prosody":[7,25,47,74,91],"modelling":[8,48],"successfully":[9],"improve":[10],"the":[11,24,63,72,90,97,113],"voice":[12],"quality":[13],"naturalness":[15],"in":[16,93],"text-to-speech":[17],"synthesis.":[18],"However,":[19],"most":[20],"of":[21,99],"them":[22],"model":[23,71],"with":[26],"a":[27,32,52,76,105],"unimodal":[28],"distribution":[29],"such":[30],"like":[31],"single":[33,77],"Gaussian,":[34],"which":[35],"is":[36],"not":[37,86],"reasonable":[38],"enough.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,50],"focus":[44],"where":[49],"introduce":[51],"Gaussian":[53],"mixture":[54,57,115],"model(GMM)":[55],"based":[56],"density":[58,116],"network.":[59],"Our":[60],"experiments":[61],"LJSpeech":[64],"dataset":[65],"demonstrate":[66],"that":[67,83,111],"GMM":[68],"can":[69],"better":[70,106],"than":[75],"Gaussian.":[78],"The":[79],"subjective":[80],"evaluations":[81],"suggest":[82],"our":[84],"method":[85],"only":[87,119],"significantly":[88],"improves":[89],"diversity":[92],"synthetic":[94],"speech":[95],"without":[96],"need":[98],"manual":[100],"control,":[101],"but":[102],"also":[103,109],"achieves":[104],"naturalness.":[107],"We":[108],"find":[110],"using":[112],"additional":[114],"network":[117],"has":[118],"very":[120],"limited":[121],"influence":[122],"inference":[124],"speed.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-03-15T00:00:00"}