{"id":"https://openalex.org/W2398071208","doi":"https://doi.org/10.1109/icassp.2016.7472732","title":"A KL divergence and DNN approach to cross-lingual TTS","display_name":"A KL divergence and DNN approach to cross-lingual TTS","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398071208","doi":"https://doi.org/10.1109/icassp.2016.7472732","mag":"2398071208"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5101692260","display_name":"Fenglong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"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":"Feng-Long Xie","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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/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 Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398343","display_name":"Haifeng Li","orcid":"https://orcid.org/0000-0002-2534-2299"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Li","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101692260"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":5.9987,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96332858,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":null,"first_page":"5515","last_page":"5519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983000159263611,"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":0.9970999956130981,"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/divergence","display_name":"Divergence (linguistics)","score":0.6555899381637573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6070613861083984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49791669845581055},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.43568509817123413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36244192719459534},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15048372745513916}],"concepts":[{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6555899381637573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6070613861083984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49791669845581055},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.43568509817123413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36244192719459534},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15048372745513916},{"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/icassp.2016.7472732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W36870606","https://openalex.org/W102093577","https://openalex.org/W1519698338","https://openalex.org/W1562777581","https://openalex.org/W1965555277","https://openalex.org/W2114010348","https://openalex.org/W2123771434","https://openalex.org/W2136922672","https://openalex.org/W2146927751","https://openalex.org/W2147768505","https://openalex.org/W2154920538","https://openalex.org/W2394932179","https://openalex.org/W2395500689","https://openalex.org/W2398741870","https://openalex.org/W6601527497","https://openalex.org/W6682918086"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W1554844486","https://openalex.org/W1520875569","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W2199957582","https://openalex.org/W2033178790"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,32,38,139,151],"Kullback-Leibler":[3],"divergence":[4],"(KLD)":[5],"and":[6,37,127],"deep":[7],"neural":[8],"net":[9],"(DNN)":[10],"based":[11],"approach":[12],"to":[13,26,85,95,113,118,149],"cross-lingual":[14],"TTS":[15,48,63,93],"(CL-TTS)":[16],"training.":[17],"A":[18],"speaker":[19,29,34,40,44,116,121],"independent":[20],"DNN":[21],"(SI-DNN)":[22],"ASR":[23,69],"is":[24,83,146],"used":[25,84],"equalize":[27],"the":[28,54,61,67,87,90,96,101,119],"difference":[30],"between":[31],"source":[33,91,120,133],"in":[35,41,53,66,70,77,89,100,122],"L1":[36,123],"reference":[39],"L2.":[42],"Two":[43],"dependent":[45],"GMM-HMM":[46],"parametric":[47],"systems":[49],"are":[50,64,129],"first":[51],"trained":[52,109],"respective":[55],"languages.":[56],"The":[57,79,105],"senones":[58,88,99],"sets":[59],"of":[60,72,143],"two":[62],"matched":[65],"SI-DNN":[68],"terms":[71],"their":[73],"output":[74],"posteriors":[75],"distributions":[76],"KLD.":[78],"minimum":[80],"KLD":[81],"criterion":[82],"transform":[86],"speaker's":[92,134],"(L1)":[94],"corresponding":[97],"\"closest\"":[98],"target":[102],"language":[103],"(L2).":[104],"new":[106],"CL-TTS":[107],"thus":[108],"has":[110],"been":[111],"shown":[112],"achieve":[114,150],"high":[115,125,152],"similarity":[117],"while":[124],"intelligibility":[126],"naturalness":[128],"preserved.":[130],"For":[131],"untranscribed":[132],"recordings,":[135],"say,":[136],"conversational":[137],"speech,":[138],"frame":[140],"mapping,":[141],"instead":[142],"\"senone":[144],"mapping\"":[145],"also":[147],"proposed":[148],"but":[153],"slightly":[154],"inferior":[155],"CL-TTS.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}