{"id":"https://openalex.org/W3016137096","doi":"https://doi.org/10.1109/icassp40776.2020.9054337","title":"Improving Prosody with Linguistic and Bert Derived Features in Multi-Speaker Based Mandarin Chinese Neural TTS","display_name":"Improving Prosody with Linguistic and Bert Derived Features in Multi-Speaker Based Mandarin Chinese Neural TTS","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016137096","doi":"https://doi.org/10.1109/icassp40776.2020.9054337","mag":"3016137096"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054337","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/A5063120829","display_name":"Yujia Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujia Xiao","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110320609","display_name":"Huaiping Ming","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiping Ming","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063120829"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":5.5188,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96480017,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6704","last_page":"6708"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9957000017166138,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8387587070465088},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8314992189407349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7674577236175537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6384924054145813},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.549098789691925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4800185263156891},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31439393758773804}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8387587070465088},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8314992189407349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674577236175537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6384924054145813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.549098789691925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4800185263156891},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31439393758773804},{"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/icassp40776.2020.9054337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054337","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":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1570629387","https://openalex.org/W2043003570","https://openalex.org/W2102003408","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2515943672","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2749651610","https://openalex.org/W2808706139","https://openalex.org/W2896457183","https://openalex.org/W2901997113","https://openalex.org/W2903853691","https://openalex.org/W2907916773","https://openalex.org/W2936103087","https://openalex.org/W2952127920","https://openalex.org/W2962936105","https://openalex.org/W2963341956","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2964281804","https://openalex.org/W2964308564","https://openalex.org/W2973217961","https://openalex.org/W2976444281","https://openalex.org/W2985056549","https://openalex.org/W3142087749","https://openalex.org/W6623517193","https://openalex.org/W6675380101","https://openalex.org/W6679434410","https://openalex.org/W6734815144","https://openalex.org/W6738277540","https://openalex.org/W6752888775","https://openalex.org/W6755207826","https://openalex.org/W6756197946","https://openalex.org/W6757322325","https://openalex.org/W6757699683","https://openalex.org/W6768248635"],"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/W2980645678"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"of":[2,16,52,58,66,105,120,160,175],"neural":[3],"TTS":[4,37,98],"have":[5,165],"made":[6],"\"human":[7],"parity\"":[8],"synthesized":[9],"speech":[10],"possible":[11],"when":[12],"a":[13,21,40,56,96,106,138,150],"large":[14],"amount":[15],"studio-quality":[17],"training":[18,103],"data":[19,104],"from":[20,32,64,149,185],"voice":[22],"talent":[23],"is":[24,38,62,187],"available.":[25],"However,":[26],"with":[27,95,137,145,181],"only":[28],"limited,":[29],"casual":[30],"recordings":[31],"an":[33],"ordinary":[34],"speaker,":[35,108],"human-like":[36],"still":[39],"big":[41],"challenge,":[42],"in":[43],"addition":[44],"to":[45,99,116],"other":[46,67],"artifacts":[47],"like":[48,71],"incomplete":[49],"sentences,":[50],"repetition":[51],"words,":[53,79],"etc.":[54],"Chinese,":[55],"language,":[57],"which":[59,191],"the":[60,101,118,188,193],"text":[61],"different":[63],"that":[65,167],"roman-letter":[68],"based":[69],"languages":[70],"English,":[72],"has":[73],"no":[74],"blank":[75],"space":[76],"between":[77],"adjacent":[78],"hence":[80],"word":[81],"segmentation":[82],"errors":[83],"can":[84],"cause":[85],"serious":[86],"semantic":[87],"confusions":[88],"and":[89,113,130,157,163],"unnatural":[90],"prosody.":[91],"In":[92],"this":[93],"study,":[94],"multi-speaker":[97],"accommodate":[100],"insufficient":[102],"target":[107],"we":[109],"investigate":[110],"linguistic":[111,132],"features":[112],"Bert-derived":[114],"information":[115],"improve":[117],"prosody":[119,174],"our":[121,176],"Mandarin":[122,177],"Chinese":[123],"TTS.":[124,178],"Three":[125],"factors":[126,169],"are":[127,170],"studied:":[128],"phone-related":[129],"prosody-related":[131],"features;":[133],"better":[134],"predicted":[135],"breaks":[136],"refined":[139],"Bert-CRF":[140],"model;":[141],"augmented":[142],"phoneme":[143],"sequence":[144],"character":[146,183],"embedding":[147],"derived":[148],"Bert":[151,186],"model.":[152],"Subjective":[153],"tests":[154],"on":[155],"in-":[156],"out-domain":[158],"tasks":[159],"News,":[161],"Chat":[162],"Audiobook,":[164],"shown":[166],"all":[168],"effective":[171],"for":[172],"improving":[173],"The":[179],"model":[180],"additional":[182],"embeddings":[184],"best":[189],"one,":[190],"outperforms":[192],"baseline":[194],"by":[195],"0.17":[196],"MOS":[197],"gain.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":7}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}