{"id":"https://openalex.org/W3015499482","doi":"https://doi.org/10.1109/icassp40776.2020.9053546","title":"Effect of Choice of Probability Distribution, Randomness, and Search Methods for Alignment Modeling in Sequence-to-Sequence Text-to-Speech Synthesis Using Hard Alignment","display_name":"Effect of Choice of Probability Distribution, Randomness, and Search Methods for Alignment Modeling in Sequence-to-Sequence Text-to-Speech Synthesis Using Hard Alignment","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015499482","doi":"https://doi.org/10.1109/icassp40776.2020.9053546","mag":"3015499482"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053546","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/A5068072475","display_name":"Yusuke Yasuda","orcid":"https://orcid.org/0000-0002-2130-747X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Yasuda","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068072475"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6724","last_page":"6728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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":0.9983999729156494,"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/randomness","display_name":"Randomness","score":0.6692586541175842},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6617329120635986},{"id":"https://openalex.org/keywords/bernoulli-distribution","display_name":"Bernoulli distribution","score":0.5945229530334473},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5776914954185486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5558157563209534},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.5346150994300842},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49778294563293457},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4165314733982086},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.4094352424144745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32471805810928345},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21987652778625488}],"concepts":[{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.6692586541175842},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6617329120635986},{"id":"https://openalex.org/C27956954","wikidata":"https://www.wikidata.org/wiki/Q391371","display_name":"Bernoulli distribution","level":3,"score":0.5945229530334473},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5776914954185486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5558157563209534},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.5346150994300842},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49778294563293457},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4165314733982086},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.4094352424144745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32471805810928345},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21987652778625488},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053546","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":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2134445663","https://openalex.org/W2519091744","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2886022419","https://openalex.org/W2892140764","https://openalex.org/W2901997113","https://openalex.org/W2946200149","https://openalex.org/W2962970071","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964260331","https://openalex.org/W2970730223","https://openalex.org/W2972702018","https://openalex.org/W2972906195","https://openalex.org/W4293714597","https://openalex.org/W6631190155","https://openalex.org/W6714142977","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6749489859","https://openalex.org/W6754925833","https://openalex.org/W6756197946","https://openalex.org/W6763832098"],"related_works":["https://openalex.org/W3034924094","https://openalex.org/W3094954546","https://openalex.org/W2039936636","https://openalex.org/W4288910996","https://openalex.org/W2152974971","https://openalex.org/W2126164081","https://openalex.org/W2184080547","https://openalex.org/W4214703581","https://openalex.org/W1970035320","https://openalex.org/W2479975675"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"text-to-speech":[1],"(TTS)":[2],"is":[3,26,101,112],"dominated":[4],"by":[5],"soft-attention-based":[6],"methods.":[7],"Recently,":[8],"hard-attention-based":[9],"methods":[10,36,57],"have":[11],"been":[12],"proposed":[13],"to":[14,85],"prevent":[15],"fatal":[16],"alignment":[17,25,41,119],"errors,":[18],"but":[19],"their":[20],"sampling":[21,35,56,68],"method":[22,49],"of":[23,34,58,93],"discrete":[24,59,87],"poorly":[27],"investigated.":[28],"This":[29],"research":[30],"investigates":[31],"various":[32],"combinations":[33],"and":[37,66,107],"probability":[38],"distributions":[39],"for":[40,117],"transition":[42],"modeling":[43],"in":[44,73],"a":[45,70,74,94],"hard-alignment-based":[46],"sequence-to-sequence":[47],"TTS":[48],"called":[50],"SSNT-TTS.":[51],"We":[52],"clarify":[53],"the":[54,81,108],"common":[55],"variables":[60,88],"including":[61],"greedy":[62],"search,":[63,65,106],"beam":[64],"random":[67],"from":[69],"Bernoulli":[71],"distribution":[72,84,111],"more":[75,89,102],"general":[76],"way.":[77],"Furthermore,":[78],"we":[79],"introduce":[80],"binary":[82,109],"Concrete":[83,110],"model":[86],"properly.":[90],"The":[91],"results":[92],"listening":[95],"test":[96],"shows":[97],"that":[98],"deterministic":[99],"search":[100,116],"preferable":[103],"than":[104],"stochastic":[105,115],"robust":[113],"with":[114],"natural":[118],"transition.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}