{"id":"https://openalex.org/W1578102511","doi":"https://doi.org/10.1109/icassp.2015.7178898","title":"Word embedding for recurrent neural network based TTS synthesis","display_name":"Word embedding for recurrent neural network based TTS synthesis","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1578102511","doi":"https://doi.org/10.1109/icassp.2015.7178898","mag":"1578102511"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5038535057","display_name":"Peilu Wang","orcid":null},"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"]},{"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":"Peilu Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Speech Group, Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Speech Group, Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"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":"Yao Qian","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":"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":"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 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/A5036050911","display_name":"Hai Zhao","orcid":"https://orcid.org/0000-0001-7290-0487"},"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":"Hai Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038535057"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":10.3546,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.98147269,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4879","last_page":"4883"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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":0.9908000230789185,"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":0.832787036895752},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7061536312103271},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6968229413032532},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.67545485496521},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6350440979003906},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.59486985206604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5024025440216064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49467727541923523},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.4737088084220886},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4602048099040985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.449036568403244},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07848852872848511}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832787036895752},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7061536312103271},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6968229413032532},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.67545485496521},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6350440979003906},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.59486985206604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5024025440216064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49467727541923523},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.4737088084220886},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4602048099040985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.449036568403244},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07848852872848511},{"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.2015.7178898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W100623710","https://openalex.org/W179875071","https://openalex.org/W1571950845","https://openalex.org/W1614298861","https://openalex.org/W1977362129","https://openalex.org/W2064675550","https://openalex.org/W2091812280","https://openalex.org/W2099062766","https://openalex.org/W2102003408","https://openalex.org/W2131774270","https://openalex.org/W2134973740","https://openalex.org/W2144499799","https://openalex.org/W2154920538","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2164019165","https://openalex.org/W2294797155","https://openalex.org/W2394662942","https://openalex.org/W2952230511","https://openalex.org/W4285719527","https://openalex.org/W6604112372","https://openalex.org/W6607333740","https://openalex.org/W6634201745","https://openalex.org/W6636510571","https://openalex.org/W6674610448","https://openalex.org/W6675380101","https://openalex.org/W6683557909","https://openalex.org/W6683738474","https://openalex.org/W6684165356","https://openalex.org/W6696843773","https://openalex.org/W6712239235"],"related_works":["https://openalex.org/W4323981018","https://openalex.org/W3158961393","https://openalex.org/W3086845375","https://openalex.org/W4312984648","https://openalex.org/W3146034405","https://openalex.org/W2949267551","https://openalex.org/W2567035470","https://openalex.org/W4321320117","https://openalex.org/W3104866047","https://openalex.org/W2791322409"],"abstract_inverted_index":{"The":[0],"current":[1],"state":[2],"of":[3,55,102,110,114],"the":[4,53,100],"art":[5],"TTS":[6,89,105],"synthesis":[7,106],"can":[8,97],"produce":[9],"synthesized":[10],"speech":[11],"with":[12,41,61],"highly":[13],"decent":[14],"quality":[15],"if":[16],"rich":[17],"segmental":[18],"and":[19,30,66,74,112],"suprasegmental":[20,26],"information":[21],"are":[22,33],"given.":[23],"However,":[24],"some":[25],"features,":[27],"e.g.,":[28],"Tone":[29],"Break":[31],"(TOBI),":[32],"time":[34],"consuming":[35],"due":[36],"to":[37,69],"being":[38,67],"manually":[39],"labeled":[40],"a":[42,71],"high":[43],"inconsistency":[44],"among":[45],"different":[46],"annotators.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"investigate":[52],"use":[54],"word":[56,60,95],"embedding,":[57],"which":[58],"represents":[59],"low":[62],"dimensional":[63],"continuous-valued":[64],"vector":[65],"assumed":[68],"carry":[70],"certain":[72],"syntactic":[73],"semantic":[75],"information,":[76],"for":[77],"bidirectional":[78],"long":[79],"short":[80],"term":[81],"memory":[82],"(BLSTM),":[83],"recurrent":[84],"neural":[85],"network":[86],"(RNN)":[87],"based":[88,104],"synthesis.":[90],"Experimental":[91],"results":[92],"show":[93],"that":[94],"embedding":[96],"significantly":[98],"improve":[99],"performance":[101],"BLSTM-RNN":[103],"without":[107],"using":[108],"features":[109],"TOBI":[111],"Part":[113],"Speech":[115],"(POS).":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}