{"id":"https://openalex.org/W3007859642","doi":"https://doi.org/10.1109/asru46091.2019.9003956","title":"Tacotron-Based Acoustic Model Using Phoneme Alignment for Practical Neural Text-to-Speech Systems","display_name":"Tacotron-Based Acoustic Model Using Phoneme Alignment for Practical Neural Text-to-Speech Systems","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007859642","doi":"https://doi.org/10.1109/asru46091.2019.9003956","mag":"3007859642"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003956","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109350986","display_name":"Yoshinori Shiga","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinori Shiga","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9970999956130981,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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":0.807671070098877},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.7655745148658752},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.659853458404541},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6583304405212402},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.604320228099823},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5774995684623718},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5354670882225037},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5310454964637756},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4868437647819519},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4775194227695465},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45246410369873047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4170215427875519},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11868906021118164},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06310102343559265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807671070098877},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7655745148658752},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.659853458404541},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6583304405212402},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.604320228099823},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5774995684623718},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5354670882225037},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5310454964637756},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4868437647819519},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4775194227695465},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45246410369873047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4170215427875519},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11868906021118164},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06310102343559265},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003956","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W198589515","https://openalex.org/W1522301498","https://openalex.org/W1576227399","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2154920538","https://openalex.org/W2169711598","https://openalex.org/W2294797155","https://openalex.org/W2296704011","https://openalex.org/W2394662942","https://openalex.org/W2508073380","https://openalex.org/W2515943672","https://openalex.org/W2519091744","https://openalex.org/W2523860356","https://openalex.org/W2584032004","https://openalex.org/W2595110011","https://openalex.org/W2598638573","https://openalex.org/W2748565458","https://openalex.org/W2749651610","https://openalex.org/W2767052532","https://openalex.org/W2769810959","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2797310469","https://openalex.org/W2801493797","https://openalex.org/W2886769154","https://openalex.org/W2889028433","https://openalex.org/W2890983311","https://openalex.org/W2899550152","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2912237252","https://openalex.org/W2914049472","https://openalex.org/W2936103087","https://openalex.org/W2936832667","https://openalex.org/W2937909162","https://openalex.org/W2938102059","https://openalex.org/W2938983457","https://openalex.org/W2939913319","https://openalex.org/W2940064443","https://openalex.org/W2942807473","https://openalex.org/W2946200149","https://openalex.org/W2962882868","https://openalex.org/W2963090522","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963272440","https://openalex.org/W2963300588","https://openalex.org/W2963522141","https://openalex.org/W2963542120","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963782041","https://openalex.org/W2963827314","https://openalex.org/W2963927338","https://openalex.org/W2963945466","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964138190","https://openalex.org/W2964168688","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970730223","https://openalex.org/W2972789651","https://openalex.org/W4289305009","https://openalex.org/W4289383906","https://openalex.org/W4294619240","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6696843773","https://openalex.org/W6697285287","https://openalex.org/W6712239235","https://openalex.org/W6732429163","https://openalex.org/W6735509194","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6753855596","https://openalex.org/W6755300632","https://openalex.org/W6756159577","https://openalex.org/W6756197946","https://openalex.org/W6758226236","https://openalex.org/W6763832098"],"related_works":["https://openalex.org/W2038801705","https://openalex.org/W2688184458","https://openalex.org/W2904846757","https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W4224231624"],"abstract_inverted_index":{"Although":[0],"sequence-to-sequence":[1],"(seq2seq)":[2],"models":[3,54,70,104],"with":[4,28,105,135,147,159,179,193],"attention":[5,48,96,140,189],"mechanism":[6],"in":[7,59,74,85],"neural":[8],"text-to-speech":[9],"(TTS)":[10],"systems,":[11],"such":[12],"as":[13],"Tacotron":[14,148],"2,":[15],"can":[16,171],"jointly":[17],"optimize":[18],"duration":[19,87,123,152],"and":[20,23,121,143,150],"acoustic":[21,103],"models,":[22,32],"realize":[24,172],"high-fidelity":[25,174],"synthesis":[26],"compared":[27,192],"conventional":[29,68],"duration-acoustic":[30],"pipeline":[31,69],"these":[33,52],"involve":[34],"a":[35,126,132,173,180,186],"risk":[36],"that":[37,167],"speech":[38],"samples":[39],"cannot":[40,55],"be":[41,56],"sometimes":[42],"successfully":[43],"synthesized":[44],"due":[45],"to":[46],"the":[47,64,67,86,122,168,194],"prediction":[49,83,97,190],"errors.":[50],"Therefore,":[51],"seq2seq":[53,133,195],"directly":[57],"introduced":[58],"practical":[60,75,92],"TTS":[61,76,93,175],"systems.":[62],"On":[63],"other":[65],"hand,":[66],"are":[71,80,114],"broadly":[72],"used":[73],"systems":[77,94],"since":[78],"there":[79],"few":[81],"crucial":[82],"errors":[84,191],"model.":[88],"For":[89],"realizing":[90],"high-quality":[91],"without":[95,188],"errors,":[98],"this":[99],"paper":[100],"investigates":[101],"Tacotron-based":[102],"phoneme":[106,112,151],"alignment":[107,120,137],"instead":[108,138],"of":[109,139,157,183],"attention.":[110],"The":[111,155],"durations":[113],"first":[115],"obtained":[116],"from":[117],"HMM-based":[118],"forced":[119,136],"model":[124,134,146,170],"is":[125,141,153],"simple":[127],"bidirectional":[128],"LSTM-based":[129],"network.":[130],"Then,":[131],"investigated":[142],"an":[144],"alternative":[145],"decoder":[149],"proposed.":[154],"results":[156],"experiments":[158],"full-context":[160],"label":[161],"input":[162],"using":[163,185],"WaveGlow":[164],"vocoder":[165],"indicate":[166],"proposed":[169],"system":[176],"for":[177],"Japanese":[178],"real-time":[181],"factor":[182],"0.13":[184],"GPU":[187],"models.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}