{"id":"https://openalex.org/W2767052532","doi":"https://doi.org/10.1109/icassp.2018.8461829","title":"Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention","display_name":"Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2767052532","doi":"https://doi.org/10.1109/icassp.2018.8461829","mag":"2767052532"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.08969","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039623511","display_name":"H. Tachibana","orcid":"https://orcid.org/0000-0001-5162-1294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hideyuki Tachibana","raw_affiliation_strings":["PKSHA Technology, Inc., Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PKSHA Technology, Inc., Bunkyo, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076069333","display_name":"Katsuya Uenoyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katsuya Uenoyama","raw_affiliation_strings":["PKSHA Technology, Inc., Bunkyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PKSHA Technology, Inc., Bunkyo, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064928213","display_name":"Shunsuke Aihara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunsuke Aihara","raw_affiliation_strings":["Independent Researcher, Shinjuku, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher, Shinjuku, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":27.983,"has_fulltext":false,"cited_by_count":285,"citation_normalized_percentile":{"value":0.99624074,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4784","last_page":"4788"},"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":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8419440984725952},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7561466097831726},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7117605209350586},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6113575100898743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5342898368835449},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5205832123756409},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4913860857486725},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4371792674064636},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4135701358318329},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3884347379207611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419440984725952},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7561466097831726},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7117605209350586},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6113575100898743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342898368835449},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5205832123756409},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4913860857486725},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4371792674064636},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4135701358318329},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3884347379207611}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8461829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.08969","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.08969","pdf_url":"https://arxiv.org/pdf/1710.08969","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.08969","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.08969","pdf_url":"https://arxiv.org/pdf/1710.08969","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1536929369","https://openalex.org/W1576227399","https://openalex.org/W1591706642","https://openalex.org/W1677182931","https://openalex.org/W1832693441","https://openalex.org/W2041741035","https://openalex.org/W2102003408","https://openalex.org/W2120847449","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2159300614","https://openalex.org/W2160473997","https://openalex.org/W2170240176","https://openalex.org/W2294797155","https://openalex.org/W2399057275","https://openalex.org/W2519091744","https://openalex.org/W2539406037","https://openalex.org/W2540404261","https://openalex.org/W2553397501","https://openalex.org/W2564591810","https://openalex.org/W2567070169","https://openalex.org/W2591927543","https://openalex.org/W2613904329","https://openalex.org/W2619368999","https://openalex.org/W2901997113","https://openalex.org/W2949382160","https://openalex.org/W2950621961","https://openalex.org/W2952436057","https://openalex.org/W2962883855","https://openalex.org/W2963012544","https://openalex.org/W2963609956","https://openalex.org/W2963840672","https://openalex.org/W2964024144","https://openalex.org/W2964060510","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2964281804","https://openalex.org/W2964308564","https://openalex.org/W4301368689","https://openalex.org/W6623987585","https://openalex.org/W6626481562","https://openalex.org/W6631190155","https://openalex.org/W6635590879","https://openalex.org/W6675380101","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6683323910","https://openalex.org/W6683480319","https://openalex.org/W6685053522","https://openalex.org/W6696085341","https://openalex.org/W6696843773","https://openalex.org/W6712515775","https://openalex.org/W6734815144","https://openalex.org/W6737778391","https://openalex.org/W6738277540","https://openalex.org/W6756197946","https://openalex.org/W6764398373"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W1889624880"],"abstract_inverted_index":{"This":[0],"paper":[1,95],"describes":[2],"a":[3,27,53,58],"novel":[4],"text-to-speech":[5],"(TTS)":[6],"technique":[7,29,37],"based":[8,104],"on":[9,70,106],"deep":[10],"convolutional":[11],"neural":[12,22,44,102],"networks":[13,23],"(CNN),":[14],"without":[15],"use":[16],"of":[17,88,93,112,140],"any":[18],"recurrent":[19],"units.":[20],"Recurrent":[21],"(RNN)":[24],"have":[25,74],"become":[26],"standard":[28],"to":[30,97],"model":[31],"sequential":[32],"data":[33],"recently,":[34],"and":[35],"this":[36,94],"has":[38],"been":[39],"used":[40],"in":[41],"some":[42],"cutting-edge":[43],"TTS":[45,103,121],"techniques.":[46],"However,":[47],"training":[48],"RNN":[49],"components":[50],"often":[51],"requires":[52],"very":[54,59],"powerful":[55],"computer,":[56],"or":[57,65],"long":[60],"time,":[61],"typically":[62],"several":[63],"days":[64],"weeks.":[66],"Recent":[67],"other":[68,72],"studies,":[69],"the":[71,117,138,141],"hand,":[73],"shown":[75],"that":[76,99],"CNN-based":[77],"sequence":[78],"synthesis":[79],"can":[80],"be":[81],"much":[82],"faster":[83],"than":[84],"RNN-based":[85],"techniques,":[86],"because":[87],"high":[89],"parallelizability.":[90],"The":[91],"objective":[92],"is":[96],"show":[98],"an":[100,129],"alternative":[101],"only":[105],"CNN":[107],"alleviate":[108],"these":[109],"economic":[110],"costs":[111],"training.":[113],"In":[114],"our":[115],"experiment,":[116],"proposed":[118],"Deep":[119],"Convolutional":[120],"was":[122,144],"sufficiently":[123],"trained":[124],"overnight":[125],"(15":[126],"hours),":[127],"using":[128],"ordinary":[130],"gaming":[131],"PC":[132],"equipped":[133],"with":[134],"two":[135],"GPUs,":[136],"while":[137],"quality":[139],"synthesized":[142],"speech":[143],"almost":[145],"acceptable.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":58},{"year":2021,"cited_by_count":54},{"year":2020,"cited_by_count":65},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":10}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2017-11-10T00:00:00"}