{"id":"https://openalex.org/W2972702018","doi":"https://doi.org/10.21437/interspeech.2019-1972","title":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS","display_name":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972702018","doi":"https://doi.org/10.21437/interspeech.2019-1972","mag":"2972702018"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1972","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5103220846","display_name":"Mutian He","orcid":"https://orcid.org/0000-0002-8939-4207"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mutian He","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079798556","display_name":"Yan Deng","orcid":"https://orcid.org/0000-0002-0778-6144"},"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":"Yan Deng","raw_affiliation_strings":["Microsoft China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","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 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5447,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.97896081,"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":"1293","last_page":"1297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10028","display_name":"Topic Modeling","score":0.9897000193595886,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9372000098228455,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7178283333778381},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.6640620231628418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5925583839416504},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5479922890663147},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4702041745185852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36770033836364746},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3306448757648468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17557436227798462},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10349145531654358}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7178283333778381},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6640620231628418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5925583839416504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5479922890663147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4702041745185852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36770033836364746},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3306448757648468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17557436227798462},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10349145531654358},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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:10.21437/interspeech.2019-1972","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1810943226","https://openalex.org/W1902237438","https://openalex.org/W2125308790","https://openalex.org/W2133564696","https://openalex.org/W2178654303","https://openalex.org/W2253795368","https://openalex.org/W2519091744","https://openalex.org/W2605141709","https://openalex.org/W2619122421","https://openalex.org/W2625720409","https://openalex.org/W2745439869","https://openalex.org/W2758584285","https://openalex.org/W2767052532","https://openalex.org/W2767601419","https://openalex.org/W2886769154","https://openalex.org/W2890909908","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964243274"],"related_works":["https://openalex.org/W4380682190","https://openalex.org/W4315701745","https://openalex.org/W1990290471","https://openalex.org/W2945307361","https://openalex.org/W1977981177","https://openalex.org/W2051487156","https://openalex.org/W2005710836","https://openalex.org/W2102386043","https://openalex.org/W2003813852","https://openalex.org/W2073681303"],"abstract_inverted_index":{"Neural":[0],"TTS":[1,83],"has":[2],"demonstrated":[3],"strong":[4],"capabilities":[5],"to":[6,18,28,69,113],"generate":[7],"human-like":[8],"speech":[9],"with":[10,26,41,84],"high":[11],"quality":[12],"and":[13,95,118],"naturalness,":[14],"while":[15],"its":[16],"generalization":[17],"out-of-domain":[19,74,134],"texts":[20],"is":[21],"still":[22],"a":[23,59],"challenging":[24],"task,":[25],"regard":[27],"the":[29,52,71,78,91,124,143],"design":[30],"of":[31],"attention-based":[32],"sequence-tosequence":[33],"acoustic":[34,67],"modeling.Various":[35],"errors":[36],"occur":[37],"in":[38,65,82,131],"those":[39],"inputs":[40,94],"unseen":[42],"context,":[43],"including":[44],"attention":[45,63,89,109],"collapse,":[46],"skipping,":[47],"repeating,":[48],"etc.,":[49],"which":[50],"limits":[51],"broader":[53],"applications.In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"novel":[60],"stepwise":[61],"monotonic":[62,80,87,102],"method":[64,76,126],"sequence-to-sequence":[66],"modeling":[68],"improve":[70],"robustness":[72,132],"on":[73,86,107,133,142],"inputs.The":[75],"utilizes":[77],"strict":[79],"property":[81],"constraints":[85],"hard":[88],"that":[90,123],"alignments":[92],"between":[93,116],"outputs":[96],"sequence":[97],"must":[98],"be":[99,111],"not":[100],"only":[101],"but":[103],"allowing":[104],"no":[105],"skipping":[106],"inputs.Soft":[108],"could":[110,127],"used":[112],"evade":[114],"mismatch":[115],"training":[117],"inference.The":[119],"experimental":[120],"results":[121],"show":[122],"proposed":[125],"achieve":[128],"significant":[129],"improvements":[130],"scenarios":[135],"for":[136],"phoneme-based":[137],"models,":[138],"without":[139],"any":[140],"regression":[141],"in-domain":[144],"naturalness":[145],"test.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}