{"id":"https://openalex.org/W4392903192","doi":"https://doi.org/10.1109/icassp48485.2024.10446023","title":"StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations","display_name":"StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903192","doi":"https://doi.org/10.1109/icassp48485.2024.10446023"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100358497","display_name":"Sen Liu","orcid":"https://orcid.org/0000-0003-2230-7671"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579214","display_name":"Yiwei Guo","orcid":"https://orcid.org/0009-0003-8114-2085"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"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":"11521","last_page":"11525"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8100130558013916},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6588647961616516},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.567626953125},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4753648638725281},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.4619581699371338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41254448890686035},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26735734939575195},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.08762288093566895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100130558013916},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6588647961616516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.567626953125},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4753648638725281},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.4619581699371338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41254448890686035},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26735734939575195},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.08762288093566895},{"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/icassp48485.2024.10446023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3405895753","display_name":null,"funder_award_id":"92370206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2085628288","https://openalex.org/W2747874407","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2973217961","https://openalex.org/W3197216873","https://openalex.org/W3198020407","https://openalex.org/W3198429080","https://openalex.org/W3198533616","https://openalex.org/W3209059054","https://openalex.org/W4221167022","https://openalex.org/W4226132755","https://openalex.org/W4285603330","https://openalex.org/W4385245566","https://openalex.org/W4385571411","https://openalex.org/W4385822745","https://openalex.org/W4395958010","https://openalex.org/W6631362777","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6796464841","https://openalex.org/W6847363464","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W3204019825"],"abstract_inverted_index":{"While":[0],"acoustic":[1,41,137],"expressiveness":[2,13,38,70,120,152],"has":[3],"long":[4],"been":[5],"studied":[6],"in":[7,14,40,71,160],"expressive":[8],"text-to-speech":[9],"(ETTS),":[10],"the":[11,46,132,156],"inherent":[12],"text":[15,115],"lacks":[16],"sufficient":[17],"attention,":[18],"especially":[19],"for":[20,61,97],"ETTS":[21,33,127],"of":[22,48,106],"artistic":[23],"works.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,83],"introduce":[29],"StoryTTS,":[30],"a":[31,49,92],"highly":[32,109],"dataset":[34],"that":[35,144],"contains":[36,103],"rich":[37,118],"both":[39],"and":[42,55,66,88,108,117,136],"textual":[43,62,69,119,135,158],"perspective,":[44],"from":[45],"recording":[47],"Mandarin":[50],"storytelling":[51],"show.":[52],"A":[53],"systematic":[54],"comprehensive":[56],"labeling":[57],"framework":[58],"is":[59],"proposed":[60],"expressiveness.":[63],"We":[64],"analyze":[65],"define":[67],"speech-related":[68],"StoryTTS":[72,123],"to":[73,129,142],"include":[74],"five":[75],"distinct":[76],"dimensions":[77],"through":[78],"linguistics,":[79],"rhetoric,":[80],"etc.":[81],"Then":[82],"employ":[84],"large":[85],"language":[86],"models":[87,146],"prompt":[89],"them":[90],"with":[91,113,150,155],"few":[93],"manual":[94],"annotation":[95],"examples":[96],"batch":[98],"annotation.":[99],"The":[100],"resulting":[101],"corpus":[102],"61":[104],"hours":[105],"consecutive":[107],"prosodic":[110],"speech":[111,149],"equipped":[112],"accurate":[114],"transcriptions":[116],"annotations.":[121],"Therefore,":[122],"can":[124,147],"aid":[125],"future":[126],"research":[128],"fully":[130],"mine":[131],"abundant":[133],"intrinsic":[134],"features.":[138],"Experiments":[139],"are":[140],"conducted":[141],"validate":[143],"TTS":[145],"generate":[148],"improved":[151],"when":[153],"integrating":[154],"annotated":[157],"labels":[159],"StoryTTS.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}