{"id":"https://openalex.org/W3160168453","doi":"https://doi.org/10.1109/icassp39728.2021.9414671","title":"Syntactic Representation Learning For Neural Network Based TTS with Syntactic Parse Tree Traversal","display_name":"Syntactic Representation Learning For Neural Network Based TTS with Syntactic Parse Tree Traversal","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160168453","doi":"https://doi.org/10.1109/icassp39728.2021.9414671","mag":"3160168453"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414671","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/A5048029954","display_name":"Changhe Song","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Changhe Song","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047338075","display_name":"Jingbei Li","orcid":"https://orcid.org/0000-0002-6284-5979"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jingbei Li","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089348821","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0000-0003-4984-2252"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I889458895","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66816502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6064","last_page":"6068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/computer-science","display_name":"Computer science","score":0.8381352424621582},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7099913358688354},{"id":"https://openalex.org/keywords/parse-tree","display_name":"Parse tree","score":0.6987063884735107},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6899573802947998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6693884134292603},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.6143072247505188},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5907999277114868},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5057549476623535},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.5012562274932861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4122500717639923},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.10424524545669556},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07421848177909851}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381352424621582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7099913358688354},{"id":"https://openalex.org/C2781466058","wikidata":"https://www.wikidata.org/wiki/Q627921","display_name":"Parse tree","level":3,"score":0.6987063884735107},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6899573802947998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6693884134292603},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.6143072247505188},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5907999277114868},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5057549476623535},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.5012562274932861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4122500717639923},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.10424524545669556},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07421848177909851}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414671","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6700000166893005,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W28194048","https://openalex.org/W162654330","https://openalex.org/W2042463830","https://openalex.org/W2120847449","https://openalex.org/W2146113428","https://openalex.org/W2157331557","https://openalex.org/W2161876018","https://openalex.org/W2395158881","https://openalex.org/W2507550121","https://openalex.org/W2901997113","https://openalex.org/W2963609956","https://openalex.org/W2963643701","https://openalex.org/W2963691546","https://openalex.org/W2963913268","https://openalex.org/W2964243274","https://openalex.org/W2972885185","https://openalex.org/W3035576098","https://openalex.org/W6601083237","https://openalex.org/W6606697926","https://openalex.org/W6684199216","https://openalex.org/W6711954399","https://openalex.org/W6749489859","https://openalex.org/W6756197946","https://openalex.org/W6757983858"],"related_works":["https://openalex.org/W2734940843","https://openalex.org/W4244615522","https://openalex.org/W1972256049","https://openalex.org/W2338828339","https://openalex.org/W2049995120","https://openalex.org/W2166677757","https://openalex.org/W2141288413","https://openalex.org/W1966257934","https://openalex.org/W3123688778","https://openalex.org/W1634973882"],"abstract_inverted_index":{"Syntactic":[0,85],"structure":[1,11,37,68],"of":[2,12,24,119,122,139,146],"a":[3,25,52,99],"sentence":[4],"text":[5],"is":[6,16,111],"correlated":[7],"with":[8,39,150,167,174],"the":[9,13,20,66,115,120,136,144,168,186],"prosodic":[10,179],"speech":[14],"that":[15],"crucial":[17],"for":[18,172],"improving":[19],"prosody":[21],"and":[22,78,117,128,160],"naturalness":[23],"text-to-speech":[26],"(TTS)":[27],"system.":[28],"Nowadays":[29],"TTS":[30],"systems":[31],"usually":[32],"try":[33],"to":[34,63,113,133,158],"incorporate":[35],"syntactic":[36,53,59,67,126,176],"information":[38],"manually":[40],"designed":[41],"features":[42],"based":[43,57],"on":[44,58],"expert":[45],"knowledge.":[46],"In":[47,170],"this":[48],"paper,":[49],"we":[50],"propose":[51],"representation":[54],"learning":[55],"method":[56],"parse":[60,83,177],"tree":[61],"traversal":[62],"automatically":[64],"utilize":[65],"information.":[69],"Two":[70],"constituent":[71,82,95,123],"label":[72,96],"sequences":[73],"are":[74,87,131],"linearized":[75],"through":[76],"left-first":[77],"right-first":[79],"traversals":[80],"from":[81,93,156,185],"tree.":[84],"representations":[86,127],"then":[88],"extracted":[89],"at":[90],"word":[91],"level":[92],"each":[94],"sequence":[97],"by":[98,164],"corresponding":[100],"uni-directional":[101],"gated":[102],"recurrent":[103],"unit":[104],"(GRU)":[105],"network.":[106],"Meanwhile,":[107],"nuclear-norm":[108],"maximization":[109],"loss":[110],"introduced":[112],"enhance":[114],"discriminability":[116],"diversity":[118],"embeddings":[121,130],"labels.":[124],"Upsampled":[125],"phoneme":[129],"concatenated":[132],"serve":[134],"as":[135],"encoder":[137],"input":[138],"Tacotron2.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"effectiveness":[145],"our":[147],"proposed":[148],"approach,":[149],"mean":[151],"opinion":[152],"score":[153],"(MOS)":[154],"increasing":[155],"3.70":[157],"3.82":[159],"ABX":[161],"preference":[162],"exceeding":[163],"17%":[165],"compared":[166],"baseline.":[169],"addition,":[171],"sentences":[173],"multiple":[175],"trees,":[178],"differences":[180],"can":[181],"be":[182],"clearly":[183],"perceived":[184],"synthesized":[187],"speeches.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}