{"id":"https://openalex.org/W4406461319","doi":"https://doi.org/10.1109/slt61566.2024.10832301","title":"Attention-Constrained Inference For Robust Decoder-Only Text-to-Speech","display_name":"Attention-Constrained Inference For Robust Decoder-Only Text-to-Speech","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461319","doi":"https://doi.org/10.1109/slt61566.2024.10832301"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5103183873","display_name":"Hankun Wang","orcid":"https://orcid.org/0000-0003-0338-1809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hankun Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579214","display_name":"Yiwei Guo","orcid":"https://orcid.org/0009-0003-8114-2085"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725200","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0001-9521-5925"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data The Chinese University of Hong Kong,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329117","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-5801-2571"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074843536","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0003-2436-5162"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute; X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103183873"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.0336,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82271033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"630","last_page":"637"},"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":0.996399998664856,"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":0.9957000017166138,"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":0.7446965575218201},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6939163208007812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6409164071083069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42469972372055054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446965575218201},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6939163208007812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6409164071083069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42469972372055054}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":38,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1583837637","https://openalex.org/W2767052532","https://openalex.org/W2896457183","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W3026874504","https://openalex.org/W3196475561","https://openalex.org/W3209059054","https://openalex.org/W4226132755","https://openalex.org/W4292779060","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4322718191","https://openalex.org/W4390075359","https://openalex.org/W4391272929","https://openalex.org/W4391833199","https://openalex.org/W4392903704","https://openalex.org/W4392904491","https://openalex.org/W4393147067","https://openalex.org/W4394671563","https://openalex.org/W6631362777","https://openalex.org/W6755207826","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6779871621","https://openalex.org/W6790356757","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6850625674","https://openalex.org/W6853515095","https://openalex.org/W6857062747","https://openalex.org/W6861267420"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"popular":[1],"decoder-only":[2,49],"text-to-speech":[3],"models":[4,16],"are":[5,139],"known":[6],"for":[7],"their":[8],"ability":[9],"of":[10,28,47,63,121],"generating":[11],"natural-sounding":[12],"speech.":[13],"However,":[14],"such":[15],"sometimes":[17],"suffer":[18],"from":[19,38],"word":[20],"skipping":[21],"and":[22,56,102,136],"repeating":[23],"due":[24],"to":[25,89,128],"the":[26,39,48,52,60,82,98,119,134],"lack":[27],"explicit":[29],"monotonic":[30,91],"alignment":[31],"constraints.":[32],"In":[33],"this":[34,72],"paper,":[35],"we":[36,74],"notice":[37],"attention":[40,45,61],"maps":[41,62],"that":[42,118],"some":[43],"particular":[44],"heads":[46,65],"model":[50,115],"indicate":[51],"alignments":[53],"between":[54],"speech":[55,123],"text.":[57],"We":[58],"call":[59],"those":[64],"Alignment-Emerged":[66],"Attention":[67,99],"Maps":[68],"(AEAMs).":[69],"Based":[70],"on":[71,107,112],"discovery,":[73],"propose":[75],"a":[76],"novel":[77],"inference":[78],"method":[79],"without":[80],"altering":[81],"training":[83],"process,":[84],"named":[85],"Attention-Constrained":[86],"Inference":[87],"(ACI),":[88],"facilitate":[90],"synthesis.":[92],"It":[93],"first":[94],"identifies":[95],"AEAMs":[96],"using":[97],"Sweeping":[100],"algorithm":[101],"then":[103],"applies":[104],"constraining":[105],"masks":[106],"AEAMs.":[108],"Our":[109],"experimental":[110],"results":[111],"decoderonly":[113],"TTS":[114],"VALL-E":[116],"show":[117],"WER":[120],"synthesized":[122],"is":[124],"reduced":[125],"by":[126],"up":[127],"20.5%":[129],"relatively":[130],"with":[131],"ACI":[132],"while":[133],"naturalness":[135],"speaker":[137],"similarity":[138],"comparable.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}