{"id":"https://openalex.org/W4297841709","doi":"https://doi.org/10.21437/interspeech.2022-11173","title":"A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis","display_name":"A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841709","doi":"https://doi.org/10.21437/interspeech.2022-11173"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11173","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5061759376","display_name":"Qibing Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibing Bai","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["ByteDance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433744","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-4087-6544"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9415000081062317,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9415000081062317,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.919700026512146,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9075000286102295,"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/intonation","display_name":"Intonation (linguistics)","score":0.8540562987327576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.682209312915802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6054926514625549},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5638646483421326},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4276973605155945},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3946428894996643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34486931562423706},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2612955868244171}],"concepts":[{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.8540562987327576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682209312915802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6054926514625549},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5638646483421326},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4276973605155945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3946428894996643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34486931562423706},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2612955868244171},{"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:10.21437/interspeech.2022-11173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11173","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":28,"referenced_works":["https://openalex.org/W162654330","https://openalex.org/W1522301498","https://openalex.org/W2107740512","https://openalex.org/W2107860279","https://openalex.org/W2519091744","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2889519245","https://openalex.org/W2896457183","https://openalex.org/W2946200149","https://openalex.org/W2948947170","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972885185","https://openalex.org/W2973217961","https://openalex.org/W2990883660","https://openalex.org/W3016137096","https://openalex.org/W3016160783","https://openalex.org/W3144035034","https://openalex.org/W3160168453","https://openalex.org/W3160844600","https://openalex.org/W3161113899","https://openalex.org/W3162948689","https://openalex.org/W3163339651","https://openalex.org/W3197324626","https://openalex.org/W3198311967","https://openalex.org/W4289383906","https://openalex.org/W4295731579"],"related_works":["https://openalex.org/W1575188933","https://openalex.org/W2021035068","https://openalex.org/W2382821289","https://openalex.org/W2800990999","https://openalex.org/W2554525739","https://openalex.org/W1494405802","https://openalex.org/W112515744","https://openalex.org/W1607387412","https://openalex.org/W2150511655","https://openalex.org/W2142042197"],"abstract_inverted_index":{"In":[0],"human":[1],"speech,":[2],"the":[3,14,22,56,68,90,119,124],"attitude":[4],"of":[5,47,58],"a":[6,95,111],"speaker":[7],"cannot":[8],"be":[9],"fully":[10],"expressed":[11],"only":[12],"by":[13],"textual":[15],"content.It":[16],"has":[17,62],"to":[18,55,66,88],"come":[19],"along":[20],"with":[21,37,70,94],"intonation.Declarative":[23],"questions":[24],"are":[25,34,44],"commonly":[26],"used":[27],"in":[28,76],"daily":[29],"Cantonese":[30,91,112],"conversations,":[31],"and":[32,103,128],"they":[33],"usually":[35],"uttered":[36],"rising":[38,49,78],"intonation.Vanilla":[39],"neural":[40],"text-to-speech":[41],"(TTS)":[42],"systems":[43,69],"not":[45,81],"capable":[46],"synthesizing":[48],"intonation":[50,79],"for":[51],"these":[52],"sentences":[53],"due":[54],"loss":[57],"semantic":[59],"information.Though":[60],"it":[61],"become":[63],"more":[64],"common":[65],"complement":[67,89],"extra":[71],"language":[72],"models,":[73],"their":[74,105],"performance":[75,127],"modeling":[77],"is":[80],"well":[82],"studied.In":[83],"this":[84],"paper,":[85],"we":[86],"propose":[87],"TTS":[92],"model":[93],"BERT-based":[96],"statement/question":[97],"classifier.We":[98],"design":[99],"different":[100],"training":[101,121],"strategies":[102],"compare":[104],"performance.We":[106],"conduct":[107],"our":[108],"experiments":[109],"on":[110],"corpus":[113],"named":[114],"CanTTS.Empirical":[115],"results":[116],"show":[117],"that":[118],"separate":[120],"approach":[122],"obtains":[123],"best":[125],"generalization":[126],"feasibility.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}