{"id":"https://openalex.org/W3162746464","doi":"https://doi.org/10.1109/icassp39728.2021.9415078","title":"A Chapter-Wise Understanding System for Text-To-Speech in Chinese Novels","display_name":"A Chapter-Wise Understanding System for Text-To-Speech in Chinese Novels","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162746464","doi":"https://doi.org/10.1109/icassp39728.2021.9415078","mag":"3162746464"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5026109787","display_name":"Junjie Pan","orcid":"https://orcid.org/0000-0002-7570-6927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Pan","raw_affiliation_strings":["Bytedance AI-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083453098","display_name":"Lin Wu","orcid":"https://orcid.org/0000-0001-6119-058X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Wu","raw_affiliation_strings":["Bytedance AI-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069496916","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0002-6554-1516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["Bytedance AI-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109120","display_name":"Pengfei Wu","orcid":"https://orcid.org/0000-0003-0896-9476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Wu","raw_affiliation_strings":["Bytedance AI-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045525954","display_name":"Chenchang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenchang Xu","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/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance AI-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]}],"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":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6069","last_page":"6073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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":0.9983000159263611,"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/naturalness","display_name":"Naturalness","score":0.8235119581222534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.782930850982666},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.65957111120224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5888810157775879},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5792112350463867},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.565866231918335},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5641564130783081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5472589731216431},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5366252064704895},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5262802243232727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4217325448989868},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32131192088127136},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3212154507637024}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8235119581222534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782930850982666},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.65957111120224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5888810157775879},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5792112350463867},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.565866231918335},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5641564130783081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5472589731216431},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5366252064704895},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5262802243232727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4217325448989868},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32131192088127136},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3212154507637024},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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":"doi:10.1109/icassp39728.2021.9415078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W75438095","https://openalex.org/W222104007","https://openalex.org/W1940872118","https://openalex.org/W2005311637","https://openalex.org/W2066064791","https://openalex.org/W2146696367","https://openalex.org/W2250268452","https://openalex.org/W2250709962","https://openalex.org/W2250849282","https://openalex.org/W2803742423","https://openalex.org/W2896457183","https://openalex.org/W2962904552","https://openalex.org/W2963270153","https://openalex.org/W2963341956","https://openalex.org/W2963429207","https://openalex.org/W2965690110","https://openalex.org/W2973080953","https://openalex.org/W3037109418","https://openalex.org/W4239946314","https://openalex.org/W4395693097","https://openalex.org/W6640362995","https://openalex.org/W6691615568","https://openalex.org/W6755207826","https://openalex.org/W6865147116"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"In":[0,39],"TTS-based":[1],"audiobook":[2],"production,":[3],"multi-role":[4],"dubbing":[5],"and":[6,27,37,54],"emotional":[7,84],"expressions":[8],"can":[9],"significantly":[10],"improve":[11],"the":[12,60],"naturalness":[13],"of":[14,21,66],"audiobooks.":[15],"However,":[16],"it":[17],"requires":[18],"manual":[19],"annotation":[20],"original":[22],"novels":[23],"with":[24,64,81],"explicit":[25],"speaker":[26,53],"emotion":[28,55],"tags":[29,56],"in":[30,103],"sentence":[31],"level,":[32],"which":[33],"is":[34],"extremely":[35],"time-consuming":[36],"costly.":[38],"this":[40],"paper,":[41],"we":[42],"propose":[43],"a":[44,82],"chapter-wise":[45],"understanding":[46],"system":[47,79],"for":[48],"Chinese":[49],"novels,":[50],"to":[51,89,94],"predict":[52],"automatically":[57],"based":[58],"on":[59],"chapter-level":[61],"context.":[62],"Compared":[63],"baselines":[65],"each":[67],"component,":[68],"our":[69,77],"models":[70],"obtain":[71],"higher":[72],"performance.":[73],"Audiobooks":[74],"produced":[75],"by":[76,97],"proposed":[78],"along":[80],"multi-speaker":[83],"TTS":[85],"system,":[86],"are":[87,101],"proved":[88],"achieve":[90],"comparable":[91],"quality":[92],"score":[93],"audiobooks":[95],"made":[96],"individual":[98],"producers.":[99],"Demos":[100],"demonstrated":[102],"https://jeffpan.net/icassp/2021/main.html.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
