{"id":"https://openalex.org/W2886769154","doi":"https://doi.org/10.1109/icassp.2018.8462020","title":"Forward Attention in Sequence- To-Sequence Acoustic Modeling for Speech Synthesis","display_name":"Forward Attention in Sequence- To-Sequence Acoustic Modeling for Speech Synthesis","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2886769154","doi":"https://doi.org/10.1109/icassp.2018.8462020","mag":"2886769154"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462020","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.06736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100688796","display_name":"Jingxuan Zhang","orcid":"https://orcid.org/0009-0005-5770-1128"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing-Xuan Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":7.4463,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.97732694,"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":"4789","last_page":"4793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976999759674072,"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":0.9947999715805054,"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/naturalness","display_name":"Naturalness","score":0.7959640026092529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7573447227478027},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7439481019973755},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.6529332995414734},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6145819425582886},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5553855299949646},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5523729920387268},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.43435490131378174},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42978763580322266},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.42634958028793335},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1407235562801361},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11699569225311279}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7959640026092529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573447227478027},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7439481019973755},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6529332995414734},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6145819425582886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5553855299949646},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5523729920387268},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.43435490131378174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42978763580322266},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42634958028793335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1407235562801361},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11699569225311279},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8462020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462020","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:1807.06736","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.06736","pdf_url":"https://arxiv.org/pdf/1807.06736","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:1807.06736","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.06736","pdf_url":"https://arxiv.org/pdf/1807.06736","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1570629387","https://openalex.org/W1810943226","https://openalex.org/W1902237438","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2060346677","https://openalex.org/W2064675550","https://openalex.org/W2079182758","https://openalex.org/W2098372067","https://openalex.org/W2102003408","https://openalex.org/W2120847449","https://openalex.org/W2127141656","https://openalex.org/W2129142580","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2178654303","https://openalex.org/W2294797155","https://openalex.org/W2327501763","https://openalex.org/W2402539796","https://openalex.org/W2515943672","https://openalex.org/W2604184139","https://openalex.org/W2608207374","https://openalex.org/W2806733747","https://openalex.org/W2901997113","https://openalex.org/W2949847915","https://openalex.org/W2949888546","https://openalex.org/W2950635152","https://openalex.org/W2964308564","https://openalex.org/W6623517193","https://openalex.org/W6638273328","https://openalex.org/W6639478124","https://openalex.org/W6670322988","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6696843773","https://openalex.org/W6713438222","https://openalex.org/W6736356763"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2135652437","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"This":[0,15],"paper":[1],"proposes":[2],"a":[3,60],"forward":[4,61,67,83,96,115],"attention":[5,51,68,75,97,109,116],"method":[6,16,98,113],"for":[7,66],"the":[8,20,23,33,38,74,94,107,112,124,131],"sequence-to-sequence":[9],"acoustic":[10,30],"modeling":[11],"of":[12,22,114,126,133],"speech":[13,128,135],"synthesis.":[14],"is":[17,69],"motivated":[18],"by":[19],"nature":[21],"monotonic":[24,39],"alignment":[25,34],"from":[26],"phone":[27],"sequences":[28],"to":[29,77,81],"sequences.":[31],"Only":[32],"paths":[35],"that":[36,93],"satisfy":[37],"condition":[40],"are":[41,56],"taken":[42],"into":[43],"consideration":[44],"at":[45,53,86],"each":[46,54,87],"decoder":[47,88],"timestep.":[48,89],"The":[49],"modified":[50],"probabilities":[52],"timestep":[55],"computed":[57],"recursively":[58],"using":[59],"algorithm.":[62],"A":[63],"transition":[64,118],"agent":[65,119],"further":[70],"proposed,":[71],"which":[72],"helps":[73],"mechanism":[76],"make":[78],"decisions":[79],"whether":[80],"move":[82],"or":[84],"stay":[85],"Experimental":[90],"results":[91],"show":[92],"proposed":[95],"achieves":[99],"faster":[100],"convergence":[101],"speed":[102,132],"and":[103,129],"higher":[104],"stability":[105],"than":[106],"baseline":[108],"method.":[110],"Besides,":[111],"with":[117],"can":[120],"also":[121],"help":[122],"improve":[123],"naturalness":[125],"synthetic":[127,134],"control":[130],"effectively.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2018-08-22T00:00:00"}
