{"id":"https://openalex.org/W4385822941","doi":"https://doi.org/10.21437/interspeech.2023-122","title":"ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading","display_name":"ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822941","doi":"https://doi.org/10.21437/interspeech.2023-122"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-122","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","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/A5063120829","display_name":"Yujia Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujia Xiao","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084317268","display_name":"Shaofei Zhang","orcid":"https://orcid.org/0000-0002-8377-2270"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Zhang","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442237","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0002-0434-7939"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100571689","display_name":"Xu Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100527744","display_name":"Sheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong 2 Microsoft, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5063120829"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.2238,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83264877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4883","last_page":"4887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.991599977016449,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.991599977016449,"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/T10028","display_name":"Topic Modeling","score":0.974399983882904,"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/T12031","display_name":"Speech and dialogue systems","score":0.9609000086784363,"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/paragraph","display_name":"Paragraph","score":0.9307628273963928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7865915894508362},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.68300461769104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5938096642494202},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5159559845924377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4097968637943268},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.33768779039382935},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13026413321495056}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.9307628273963928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865915894508362},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.68300461769104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5938096642494202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5159559845924377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097968637943268},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33768779039382935},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13026413321495056},{"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.2023-122","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2766812927","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964110616","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W3026759356","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3033529678","https://openalex.org/W3037798801","https://openalex.org/W3092028330","https://openalex.org/W3160694286","https://openalex.org/W3163339651","https://openalex.org/W3197762246","https://openalex.org/W4221165968","https://openalex.org/W4280561221","https://openalex.org/W4287121924","https://openalex.org/W4294619240","https://openalex.org/W4295036296","https://openalex.org/W4295838474","https://openalex.org/W4298580827","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W4385822941","https://openalex.org/W4395957972"],"related_works":["https://openalex.org/W3009520549","https://openalex.org/W2073813715","https://openalex.org/W2035867124","https://openalex.org/W2384896988","https://openalex.org/W4376867579","https://openalex.org/W2360340770","https://openalex.org/W1478892874","https://openalex.org/W1600546713","https://openalex.org/W2055615961","https://openalex.org/W2896274967"],"abstract_inverted_index":{"While":[0],"state-of-the-art":[1],"Text-to-Speech":[2],"systems":[3],"can":[4],"generate":[5],"natural":[6],"speech":[7,21,73],"of":[8,34],"very":[9],"high":[10,40],"quality":[11,106],"at":[12],"sentence":[13,76],"level,":[14],"they":[15],"still":[16],"meet":[17],"great":[18],"challenges":[19],"in":[20,110],"generation":[22],"for":[23,45,87],"paragraph":[24,111],"/":[25],"long-form":[26,46],"reading.Such":[27],"deficiencies":[28],"are":[29],"due":[30],"to":[31,68,83,95],"i)":[32],"ignorance":[33],"cross-sentence":[35],"contextual":[36],"information,":[37],"and":[38,42,72,107],"ii)":[39],"computation":[41],"memory":[43],"cost":[44],"synthesis.To":[47],"address":[48],"these":[49],"issues,":[50],"this":[51],"work":[52],"develops":[53],"a":[54,64],"lightweight":[55],"yet":[56],"effective":[57],"TTS":[58],"system,":[59],"ContextSpeech.Specifically,":[60],"we":[61,78,91],"first":[62],"design":[63],"memory-cached":[65],"recurrence":[66],"mechanism":[67],"incorporate":[69],"global":[70,88],"text":[71],"context":[74,89],"into":[75],"encoding.Then":[77],"construct":[79],"hierarchically-structured":[80],"textual":[81],"semantics":[82],"broaden":[84],"the":[85,104],"scope":[86],"enhancement.Additionally,":[90],"integrate":[92],"linearized":[93],"self-attention":[94],"improve":[96],"model":[97,115],"efficiency.Experiments":[98],"show":[99],"that":[100],"ContextSpeech":[101],"significantly":[102],"improves":[103],"voice":[105],"prosody":[108],"expressiveness":[109],"reading":[112],"with":[113],"competitive":[114],"efficiency.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}