{"id":"https://openalex.org/W3015586278","doi":"https://doi.org/10.1109/icassp40776.2020.9054148","title":"Improving End-to-End Speech Synthesis with Local Recurrent Neural Network Enhanced Transformer","display_name":"Improving End-to-End Speech Synthesis with Local Recurrent Neural Network Enhanced Transformer","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015586278","doi":"https://doi.org/10.1109/icassp40776.2020.9054148","mag":"3015586278"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054148","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/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["Tencent Inc, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701662","display_name":"Xinhui Li","orcid":"https://orcid.org/0000-0002-8398-8741"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhui Li","raw_affiliation_strings":["Tencent Inc, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101692260","display_name":"Fenglong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenglong Xie","raw_affiliation_strings":["Tencent Inc, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658678","display_name":"Li L\u00fc","orcid":"https://orcid.org/0000-0001-5230-3749"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Lu","raw_affiliation_strings":["Tencent Inc, China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101398585"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":2.121,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89619935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6734","last_page":"6738"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9955999851226807,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7013857960700989},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6992080807685852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6659061312675476},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6353373527526855},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5160977244377136},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4293064773082733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41381531953811646},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21017301082611084},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0657869279384613}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7013857960700989},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6992080807685852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659061312675476},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6353373527526855},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5160977244377136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4293064773082733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41381531953811646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21017301082611084},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0657869279384613},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054148","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1522301498","https://openalex.org/W1570629387","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2104075463","https://openalex.org/W2120847449","https://openalex.org/W2194775991","https://openalex.org/W2519091744","https://openalex.org/W2766406951","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2889028433","https://openalex.org/W2892140764","https://openalex.org/W2937909162","https://openalex.org/W2949382160","https://openalex.org/W2956480774","https://openalex.org/W2963091184","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963925437","https://openalex.org/W2963927338","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2973212992","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W6629609042","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6739901393","https://openalex.org/W6745232783","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6753797277","https://openalex.org/W6754925833","https://openalex.org/W6765571568","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"Although":[0],"Transformer":[1,64,76,100],"based":[2],"neural":[3,60],"end-to-end":[4],"TTS":[5],"model":[6,29,113],"has":[7],"demonstrated":[8],"extreme":[9],"effectiveness":[10],"in":[11,34,122,133,149],"capturing":[12],"long-term":[13,94],"dependencies":[14,95],"and":[15,31,75,83,124],"achieved":[16],"state-of-the-art":[17],"performance,":[18],"it":[19],"still":[20],"suffers":[21],"from":[22],"two":[23],"problems.":[24],"1)":[25],"limited":[26,44],"ability":[27],"to":[28,65,127],"sequential":[30,82],"local":[32,58,84],"structures":[33,85],"sequences;":[35],"2)":[36],"heavily":[37],"rely":[38],"on":[39,135,157],"position":[40,105],"embeddings":[41],"that":[42],"have":[43],"effect":[45],"but":[46],"require":[47],"an":[48,144],"amount":[49],"of":[50,69,72,104,120,147],"design":[51],"efforts.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"introduce":[57],"recurrent":[59],"network":[61],"(Local-RNN)":[62],"into":[63],"make":[66],"full":[67],"use":[68,103],"the":[70,93,155],"advantages":[71],"both":[73],"RNN":[74],"while":[77,92],"mitigating":[78],"their":[79],"drawbacks.":[80],"The":[81],"could":[86,96],"be":[87,97],"effectively":[88],"modeled":[89],"by":[90,99],"Local-RNN,":[91],"captured":[98],"without":[101],"any":[102],"embeddings.":[106],"Subjective":[107],"evaluation":[108],"results":[109],"show":[110,143],"our":[111],"proposed":[112],"outperforms":[114],"baseline":[115,156],"(Transformer)":[116],"with":[117],"a":[118,158],"gap":[119],"0.12":[121],"MOS":[123],"achieves":[125],"close":[126],"human":[128],"quality":[129],"(4.34":[130],"vs.":[131],"4.45":[132],"MOS)":[134],"general":[136],"test.":[137,160],"Case":[138],"level":[139,151],"intelligibility":[140,152],"test":[141],"also":[142],"absolute":[145],"improvement":[146],"6.5%":[148],"case":[150],"rate":[153],"over":[154],"challenging":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}