{"id":"https://openalex.org/W3112336664","doi":"https://doi.org/10.1109/slt48900.2021.9383530","title":"GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis","display_name":"GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3112336664","doi":"https://doi.org/10.1109/slt48900.2021.9383530","mag":"3112336664"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5022188380","display_name":"Aolan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Aolan Sun","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050643890","display_name":"Huayi Peng","orcid":"https://orcid.org/0000-0003-1985-1537"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Huayi Peng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360190","display_name":"Zhen Zeng","orcid":"https://orcid.org/0000-0003-4383-3590"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Zeng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109480959","display_name":"Lingwei Kong","orcid":"https://orcid.org/0000-0001-9654-8414"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Lingwei Kong","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":0.7326,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71171711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"438","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/prosody","display_name":"Prosody","score":0.9016762971878052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477480173110962},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.706593930721283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5820433497428894},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5644030570983887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210922956466675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5024797916412354},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.47565361857414246},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3215469717979431},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.15982770919799805},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1394755244255066}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9016762971878052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477480173110962},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.706593930721283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5820433497428894},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5644030570983887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210922956466675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5024797916412354},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.47565361857414246},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3215469717979431},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.15982770919799805},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1394755244255066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2057743259","https://openalex.org/W2116341502","https://openalex.org/W2120847449","https://openalex.org/W2130942839","https://openalex.org/W2254292464","https://openalex.org/W2309415944","https://openalex.org/W2595713599","https://openalex.org/W2766406951","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2798749466","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2904459034","https://openalex.org/W2905224888","https://openalex.org/W2907492528","https://openalex.org/W2914049472","https://openalex.org/W2932022923","https://openalex.org/W2936103087","https://openalex.org/W2937297115","https://openalex.org/W2937870435","https://openalex.org/W2950898568","https://openalex.org/W2963272440","https://openalex.org/W2963341956","https://openalex.org/W2963374482","https://openalex.org/W2963497309","https://openalex.org/W2963609956","https://openalex.org/W2963653811","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964168688","https://openalex.org/W2964243274","https://openalex.org/W2972375191","https://openalex.org/W2972699445","https://openalex.org/W2972881244","https://openalex.org/W2972885185","https://openalex.org/W2972956431","https://openalex.org/W2972956685","https://openalex.org/W2973217961","https://openalex.org/W3015621018","https://openalex.org/W4210257598","https://openalex.org/W4295731579","https://openalex.org/W6679436768","https://openalex.org/W6690815549","https://openalex.org/W6691808304","https://openalex.org/W6735019100","https://openalex.org/W6745232783","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6757374366","https://openalex.org/W6760861152"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W3149582125","https://openalex.org/W2465421051","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W1984347656"],"abstract_inverted_index":{"This":[0,168],"paper":[1],"introduces":[2],"a":[3,30,105],"graphical":[4,31,94],"representation":[5],"approach":[6,132,172],"of":[7,14,26,40,140,148,166],"prosody":[8,36,95,138,174],"boundary":[9,62,67,96],"(GraphPB)":[10],"in":[11,29,163,176],"the":[12,21,35,41,50,55,93,121,135,156,164],"task":[13],"Chinese":[15],"speech":[16,178],"synthesis,":[17],"intending":[18],"to":[19,91,116],"parse":[20],"semantic":[22],"and":[23,49,64,80,102,108,137],"syntactic":[24],"relationship":[25],"input":[27],"sequences":[28],"domain":[32],"for":[33,173],"improving":[34],"performance.":[37],"The":[38,125,143],"nodes":[39],"graph":[42,89,106],"embedding":[43],"are":[44,52,86,114],"formed":[45,53,103],"by":[46,54,104],"prosodic":[47,57,60],"words,":[48],"edges":[51],"other":[56],"boundaries,":[58],"namely":[59],"phrase":[61,66],"(PPH)":[63],"intonation":[65],"(IPH).":[68],"Different":[69],"Graph":[70,76,81],"Neural":[71,77],"Networks":[72],"(GNN)":[73],"like":[74],"Gated":[75],"Network":[78],"(GGNN)":[79],"Long":[82],"Short-term":[83],"Memory":[84],"(G-LSTM)":[85],"utilised":[87],"as":[88],"encoders":[90],"exploit":[92],"information.":[97],"Graph-to-sequence":[98],"model":[99],"is":[100],"proposed":[101,115,131],"encoder":[107],"an":[109,141,170],"attentional":[110],"decoder.":[111],"Two":[112],"techniques":[113],"embed":[117],"sequential":[118],"information":[119],"into":[120],"graph-to-sequence":[122],"text-to-speech":[123],"model.":[124],"experimental":[126],"results":[127,154],"show":[128],"that":[129],"this":[130],"can":[133],"encode":[134],"phonetic":[136],"rhythm":[139],"utterance.":[142],"mean":[144],"opinion":[145],"score":[146],"(MOS)":[147],"these":[149],"GNN":[150],"models":[151,159],"shows":[152],"comparative":[153],"with":[155,160],"state-of-the-art":[157],"sequence-to-sequence":[158],"better":[161],"performance":[162],"aspect":[165],"prosody.":[167],"provides":[169],"alternative":[171],"modelling":[175],"end-to-end":[177],"synthesis.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}