{"id":"https://openalex.org/W2942807473","doi":"https://doi.org/10.1109/access.2019.2914149","title":"Pre-Alignment Guided Attention for Improving Training Efficiency and Model Stability in End-to-End Speech Synthesis","display_name":"Pre-Alignment Guided Attention for Improving Training Efficiency and Model Stability in End-to-End Speech Synthesis","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2942807473","doi":"https://doi.org/10.1109/access.2019.2914149","mag":"2942807473"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2914149","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2914149","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08703406.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08703406.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014440768","display_name":"Xiaolian Zhu","orcid":"https://orcid.org/0000-0002-8842-7329"},"institutions":[{"id":"https://openalex.org/I113992204","display_name":"Hebei University of Economics and Business","ror":"https://ror.org/05j1kc284","country_code":"CN","type":"education","lineage":["https://openalex.org/I113992204"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolian Zhu","raw_affiliation_strings":["Public Computer Education Center, Hebei University of Economics and Business, Shijiazhuang, China"],"raw_orcid":"https://orcid.org/0000-0002-8842-7329","affiliations":[{"raw_affiliation_string":"Public Computer Education Center, Hebei University of Economics and Business, Shijiazhuang, China","institution_ids":["https://openalex.org/I113992204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649616","display_name":"Yuchao Zhang","orcid":"https://orcid.org/0009-0006-0191-3612"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchao Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.0881,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95065661,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"7","issue":null,"first_page":"65955","last_page":"65964"},"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.9979000091552734,"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":0.8424642086029053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6436676979064941},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5813471674919128},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5244339108467102},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5037080645561218},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5002398490905762},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4333485960960388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4279060661792755},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42266684770584106},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.42234736680984497},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4115757346153259},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3270605802536011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424642086029053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6436676979064941},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5813471674919128},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5244339108467102},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5037080645561218},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5002398490905762},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4333485960960388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4279060661792755},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42266684770584106},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.42234736680984497},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4115757346153259},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3270605802536011},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2914149","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2914149","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08703406.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5bb686c363c046ecb5013aa1bb13476a","is_oa":true,"landing_page_url":"https://doaj.org/article/5bb686c363c046ecb5013aa1bb13476a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 65955-65964 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2914149","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2914149","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08703406.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2915035755","display_name":null,"funder_award_id":"2017YFB1002102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320324851","display_name":"Hebei University","ror":"https://ror.org/01p884a79"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2942807473.pdf","grobid_xml":"https://content.openalex.org/works/W2942807473.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1570629387","https://openalex.org/W1810943226","https://openalex.org/W2095705004","https://openalex.org/W2102003408","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2591927543","https://openalex.org/W2605141709","https://openalex.org/W2749651610","https://openalex.org/W2766812927","https://openalex.org/W2767052532","https://openalex.org/W2806733747","https://openalex.org/W2889028433","https://openalex.org/W2892140764","https://openalex.org/W2901997113","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W3211259717","https://openalex.org/W4293714597","https://openalex.org/W4295731579","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6674330103","https://openalex.org/W6679436768","https://openalex.org/W6735706088","https://openalex.org/W6745697700","https://openalex.org/W6754925833","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2799713421","https://openalex.org/W4396816926","https://openalex.org/W2593532750","https://openalex.org/W2110442089","https://openalex.org/W2642467014","https://openalex.org/W2916997151","https://openalex.org/W3198455051"],"abstract_inverted_index":{"Recently,":[0],"end-to-end":[1],"(E2E)":[2],"neural":[3,31,132],"text-to-speech":[4],"systems,":[5,17],"such":[6,55],"as":[7,74],"Tacotron2,":[8],"have":[9],"begun":[10],"to":[11,136,141],"surpass":[12],"the":[13,33,60,68,71,80,84,101,112,131,138,142,175,192,201,216,227],"traditional":[14],"multi-stage":[15],"hand-engineered":[16],"with":[18],"both":[19],"simplified":[20],"system":[21,35,57],"building":[22],"pipelines":[23],"and":[24,48,70,83,95,114,155,187,234],"high-quality":[25],"speech.":[26,236],"With":[27],"a":[28,56,116],"unique":[29],"encoder-decoder":[30],"structure,":[32],"Tacotron2":[34,197],"no":[36],"longer":[37],"needs":[38],"separately":[39],"learned":[40],"text":[41,81],"analysis":[42],"front-end,":[43],"duration":[44,77],"model,":[45,47],"acoustic":[46,85],"audio":[49,153],"synthesis":[50],"module.":[51],"The":[52,147,171],"key":[53],"of":[54,196,221],"lies":[58],"in":[59],"attention":[61,88,120,139,180,202],"mechanism,":[62],"which":[63,99,210],"learns":[64],"an":[65,75,152,166],"alignment":[66,150,203],"between":[67,151],"encoder":[69],"decoder,":[72],"serving":[73],"implicit":[76],"model":[78,96,188],"bridging":[79],"sequence":[82,159],"sequence.":[86],"However,":[87],"learning":[89,121,140],"suffers":[90],"from":[91,104,165],"low":[92],"training":[93,185],"efficiency":[94,186],"instability":[97],"problems,":[98],"hinder":[100],"E2E":[102],"approaches":[103],"wide":[105],"deployment.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,124],"address":[111],"problems":[113],"propose":[115],"novel":[117],"pre-alignment":[118,177],"guided":[119,178],"approach.":[122],"Specifically,":[123],"inject":[125],"handy":[126],"prior":[127],"knowledge-accurate":[128],"phoneme":[129,158],"durations-in":[130],"network":[133],"loss":[134],"function":[135],"bias":[137],"desired":[143],"direction":[144],"more":[145,232],"accurately.":[146],"explicit":[148],"time":[149],"recording":[154],"its":[156],"corresponding":[157],"can":[160,182,198,230],"be":[161],"achieved":[162],"by":[163],"forced-alignment":[164],"automatic":[167],"speech":[168],"recognizer":[169],"(ASR).":[170],"experiments":[172,223],"show":[173,225],"that":[174,226],"proposed":[176],"(PAG)":[179],"approach":[181,229],"significantly":[183],"improve":[184],"stability.":[189],"More":[190],"specifically,":[191],"PAG":[193],"updated":[194],"version":[195],"quickly":[199],"obtain":[200],"using":[204],"only":[205],"500":[206],"(text,":[207],"audio)":[208],"pairs,":[209],"is":[211],"apparently":[212],"not":[213],"possible":[214],"for":[215],"original":[217],"Tacotron2.":[218],"A":[219],"series":[220],"subjective":[222],"also":[224],"PAG-Tacotron2":[228],"synthesize":[231],"stable":[233],"natural":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}