{"id":"https://openalex.org/W3196001064","doi":"https://doi.org/10.1109/icassp43922.2022.9747707","title":"One TTS Alignment to Rule Them All","display_name":"One TTS Alignment to Rule Them All","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3196001064","doi":"https://doi.org/10.1109/icassp43922.2022.9747707","mag":"3196001064"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747707","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5058296176","display_name":"Rohan Badlani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rohan Badlani","raw_affiliation_strings":["NVIDIA,Santa Clara","NVIDIA, Santa Clara"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011669714","display_name":"Adrian \u0141a\u0144cucki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrian Lancucki","raw_affiliation_strings":["NVIDIA,Santa Clara","NVIDIA, Santa Clara"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016107863","display_name":"Kevin J. Shih","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin J. Shih","raw_affiliation_strings":["NVIDIA,Santa Clara","NVIDIA, Santa Clara"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113576287","display_name":"Rafael Valle","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Valle","raw_affiliation_strings":["NVIDIA,Santa Clara","NVIDIA, Santa Clara"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947241","display_name":"Ping Wei","orcid":"https://orcid.org/0000-0002-8535-9527"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Ping","raw_affiliation_strings":["NVIDIA,Santa Clara","NVIDIA, Santa Clara"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["NVIDIA,Santa Clara","NVIDIA, Santa Clara"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058296176"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":5.301,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.96611722,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6092","last_page":"6096"},"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":0.996999979019165,"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":0.9941999912261963,"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/autoregressive-model","display_name":"Autoregressive model","score":0.8612717390060425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7987841367721558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6429269909858704},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6428622007369995},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5137721300125122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47463521361351013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09243223071098328}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8612717390060425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987841367721558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6429269909858704},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6428622007369995},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5137721300125122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47463521361351013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09243223071098328},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747707","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":40,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1810943226","https://openalex.org/W2107860279","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2604184139","https://openalex.org/W2747874407","https://openalex.org/W2767052532","https://openalex.org/W2932319281","https://openalex.org/W2946200149","https://openalex.org/W2953022181","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W2972359262","https://openalex.org/W2973215447","https://openalex.org/W3015922793","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3035083561","https://openalex.org/W3038172701","https://openalex.org/W3130016944","https://openalex.org/W3150572638","https://openalex.org/W3194000401","https://openalex.org/W6623517193","https://openalex.org/W6638273328","https://openalex.org/W6679434410","https://openalex.org/W6736356763","https://openalex.org/W6745317255","https://openalex.org/W6746700228","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778083308","https://openalex.org/W6778823374","https://openalex.org/W6779871621","https://openalex.org/W6800393981","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W3150905897","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W1520183331","https://openalex.org/W2099889858","https://openalex.org/W2168175994","https://openalex.org/W2283583712"],"abstract_inverted_index":{"Speech-to-text":[0],"alignment":[1,66,83,121],"is":[2],"a":[3],"critical":[4],"component":[5],"of":[6,78],"neural":[7,79],"text-to-speech":[8],"(TTS)":[9],"models.":[10,81],"Autoregressive":[11],"TTS":[12,51,80,105],"models":[13,52],"typically":[14],"use":[15],"an":[16,93],"attention":[17],"mechanism":[18,67],"to":[19,28,34,36,43,75,136],"learn":[20],"these":[21,25],"alignments":[22,26],"on-line.":[23],"However,":[24],"tend":[27],"be":[29],"brittle":[30],"and":[31,39,71,92,112,141],"often":[32],"fail":[33],"generalize":[35],"long":[37,139],"utterances":[38,140],"out-of-domain":[40],"text,":[41],"leading":[42],"missing":[44],"or":[45],"repeating":[46],"words.":[47],"Most":[48],"non-autoregressive":[49,113],"end-to-end":[50],"rely":[53],"on":[54,138],"durations":[55],"extracted":[56],"from":[57],"external":[58,132],"sources.":[59],"In":[60,97],"this":[61],"paper":[62],"we":[63],"leverage":[64],"the":[65,87,100,125,143],"proposed":[68],"in":[69],"RAD-TTS":[70],"demonstrate":[72],"its":[73],"applicability":[74],"wide":[76],"variety":[77],"The":[82],"learning":[84],"framework":[85,101],"combines":[86],"forward-sum":[88],"algorithm,":[89,91],"Viterbi":[90],"efficient":[94],"static":[95],"prior.":[96],"our":[98],"experiments,":[99],"improves":[102,120,142],"all":[103],"tested":[104],"architectures,":[106],"both":[107],"autoregressive":[108],"(Flowtron,":[109],"Tacotron":[110],"2)":[111],"(FastPitch,":[114],"FastSpeech":[115],"2,":[116],"RAD-TTS).":[117],"Specifically,":[118],"it":[119],"convergence":[122],"speed,":[123],"simplifies":[124],"training":[126],"pipeline":[127],"by":[128,150],"eliminating":[129],"need":[130],"for":[131],"aligners,":[133],"enhances":[134],"robustness":[135],"errors":[137],"perceived":[144],"speech":[145],"synthesis":[146],"quality,":[147],"as":[148],"judged":[149],"human":[151],"evaluators.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}