{"id":"https://openalex.org/W3015680182","doi":"https://doi.org/10.1109/icassp40776.2020.9053390","title":"A Unified Sequence-to-Sequence Front-End Model for Mandarin Text-to-Speech Synthesis","display_name":"A Unified Sequence-to-Sequence Front-End Model for Mandarin Text-to-Speech Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015680182","doi":"https://doi.org/10.1109/icassp40776.2020.9053390","mag":"3015680182"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5026109787","display_name":"Junjie Pan","orcid":"https://orcid.org/0000-0002-7570-6927"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Junjie Pan","raw_affiliation_strings":["Bytedance AI-Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874107","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0741-4831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["Bytedance AI-Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018465248","display_name":"Zhiling Zhang","orcid":"https://orcid.org/0000-0001-7807-2264"},"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":"Zhiling Zhang","raw_affiliation_strings":["Shanghai Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682515","display_name":"Shichao Liu","orcid":"https://orcid.org/0000-0002-3163-161X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shichao Liu","raw_affiliation_strings":["Bytedance AI-Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354571","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-6821-2710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Bytedance AI-Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Bytedance AI-Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI-Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5026109787"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3861,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90743937,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6689","last_page":"6693"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9973000288009644,"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":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8555953502655029},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.746192455291748},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7256057262420654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7200177311897278},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.6849356889724731},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.641257643699646},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5778385400772095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5774998068809509},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5527045130729675},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5350863337516785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115645527839661},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.48824813961982727},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13803935050964355},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09044289588928223},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07610571384429932},{"id":"https://openalex.org/keywords/particle-physics","display_name":"Particle physics","score":0.06192910671234131}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8555953502655029},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.746192455291748},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7256057262420654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200177311897278},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.6849356889724731},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.641257643699646},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5778385400772095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5774998068809509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5527045130729675},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5350863337516785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115645527839661},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.48824813961982727},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13803935050964355},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09044289588928223},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07610571384429932},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.06192910671234131},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861945760","https://openalex.org/W1973424788","https://openalex.org/W2147880316","https://openalex.org/W2150622925","https://openalex.org/W2153579005","https://openalex.org/W2162433174","https://openalex.org/W2420187884","https://openalex.org/W2561184891","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2936103087","https://openalex.org/W2948238043","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972956685","https://openalex.org/W3015651285","https://openalex.org/W4294170691","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6682082992","https://openalex.org/W6682691769","https://openalex.org/W6736996214","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6763316926"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W169399214","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W3100825170","https://openalex.org/W2549308614","https://openalex.org/W4377694462"],"abstract_inverted_index":{"In":[0,33],"Mandarin":[1,44,96],"text-to-speech":[2],"(TTS)":[3],"system,":[4],"the":[5,12,56,86,110],"front-end":[6,23,41,61,88,112],"text":[7],"processing":[8],"module":[9],"significantly":[10],"influences":[11],"intelligibility":[13],"and":[14,69,73,91,114],"naturalness":[15],"of":[16,26],"synthesized":[17,100],"speech.":[18],"Building":[19],"a":[20,38,95,105],"typical":[21],"pipeline-based":[22,57,111],"which":[24],"consists":[25],"multiple":[27],"individual":[28],"components":[29],"requires":[30],"extensive":[31],"efforts.":[32],"this":[34],"paper,":[35],"we":[36],"proposed":[37],"unified":[39,60,87],"sequence-to-sequence":[40],"model":[42],"for":[43],"TTS":[45,97],"that":[46,103],"converts":[47],"raw":[48],"texts":[49],"to":[50,55,93,116],"linguistic":[51],"features":[52],"directly.":[53],"Compared":[54],"front-end,":[58],"our":[59],"can":[62],"achieve":[63],"comparable":[64,106],"performance":[65],"in":[66,80],"polyphone":[67],"disambiguation":[68],"prosody":[70],"word":[71],"prediction,":[72],"improve":[74],"intonation":[75],"phrase":[76],"prediction":[77],"by":[78,102],"0.0738":[79],"F1":[81],"score.":[82],"We":[83],"also":[84],"implemented":[85],"with":[89,109],"Tacotron":[90],"WaveRNN":[92],"build":[94],"system.":[98],"The":[99],"speech":[101],"got":[104],"MOS":[107],"(4.38)":[108],"(4.37)":[113],"close":[115],"human":[117],"recordings":[118],"(4.49).":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}