{"id":"https://openalex.org/W4319862430","doi":"https://doi.org/10.1109/slt54892.2023.10023268","title":"Regotron: Regularizing the Tacotron2 Architecture Via Monotonic Alignment Loss","display_name":"Regotron: Regularizing the Tacotron2 Architecture Via Monotonic Alignment Loss","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862430","doi":"https://doi.org/10.1109/slt54892.2023.10023268"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023268","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/SLT54892.2023.10023268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102773432","display_name":"Efthymios Georgiou","orcid":"https://orcid.org/0000-0002-6042-9584"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Efthymios Georgiou","raw_affiliation_strings":["Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","School of ECE, National Technical University of Athens, Athens, Greece","Athena Research Center, Institute for Language and Speech Processing, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"School of ECE, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087680388","display_name":"Kosmas Kritsis","orcid":"https://orcid.org/0000-0003-4513-5040"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Kosmas Kritsis","raw_affiliation_strings":["Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","Athena Research Center, Institute for Language and Speech Processing, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026032406","display_name":"Georgios Paraskevopoulos","orcid":"https://orcid.org/0000-0003-4067-6294"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Paraskevopoulos","raw_affiliation_strings":["Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","School of ECE, National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"School of ECE, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003869083","display_name":"Athanasios Katsamanis","orcid":"https://orcid.org/0000-0002-2642-2354"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athanasios Katsamanis","raw_affiliation_strings":["Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","Athena Research Center, Institute for Language and Speech Processing, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060812182","display_name":"Vassilis Katsouros","orcid":"https://orcid.org/0000-0002-4185-2344"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Katsouros","raw_affiliation_strings":["Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","Athena Research Center, Institute for Language and Speech Processing, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing,Athena Research Center,Athens,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Athena Research Center, Institute for Language and Speech Processing, Athens, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084949286","display_name":"Alexandros Potamianos","orcid":"https://orcid.org/0009-0007-1532-5288"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandros Potamianos","raw_affiliation_strings":["School of ECE, National Technical University of Athens,Athens,Greece","School of ECE, National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of ECE, National Technical University of Athens,Athens,Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"School of ECE, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4159,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.50978373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"977","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8159747123718262},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.8083306550979614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477954626083374},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6997138857841492},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5762951374053955},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5717098712921143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5038184523582458},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47210660576820374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44556912779808044},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4440745413303375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34160614013671875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16905122995376587},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.07360237836837769}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8159747123718262},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.8083306550979614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477954626083374},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6997138857841492},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5762951374053955},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5717098712921143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5038184523582458},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47210660576820374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44556912779808044},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4440745413303375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34160614013671875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16905122995376587},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.07360237836837769},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt54892.2023.10023268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023268","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:10868287","is_oa":true,"landing_page_url":"https://doi.org/10.1109/SLT54892.2023.10023268","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SLT, 2022 IEEE Spoken Language Technology Workshop, Doha, Qatar, 9-12 January 2023","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:10868287","is_oa":true,"landing_page_url":"https://doi.org/10.1109/SLT54892.2023.10023268","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SLT, 2022 IEEE Spoken Language Technology Workshop, Doha, Qatar, 9-12 January 2023","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2122172720","display_name":null,"funder_award_id":"T2EDK04248","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7662485632","display_name":null,"funder_award_id":"T2EDK04248","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1583837637","https://openalex.org/W2130942839","https://openalex.org/W2519091744","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2767052532","https://openalex.org/W2769810959","https://openalex.org/W2915977493","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015282541","https://openalex.org/W3015478688","https://openalex.org/W3015922793","https://openalex.org/W3016136182","https://openalex.org/W3026874504","https://openalex.org/W3095828473","https://openalex.org/W3171066367","https://openalex.org/W3195077602","https://openalex.org/W3196001064","https://openalex.org/W3197294703","https://openalex.org/W3198048682","https://openalex.org/W3198633333","https://openalex.org/W3198843334","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6679436768","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6753855596","https://openalex.org/W6757079273","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778083308","https://openalex.org/W6778823374","https://openalex.org/W6779337556"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W4387098302","https://openalex.org/W3165080709","https://openalex.org/W2948317131","https://openalex.org/W4288365855","https://openalex.org/W3158195778"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"Text-to-Speech":[2],"(TTS)":[3],"systems":[4],"have":[5],"achieved":[6],"impressive":[7],"generated":[8],"speech":[9,121],"quality,":[10],"close":[11],"to":[12,76,94,124],"human":[13],"parity.":[14],"However,":[15],"they":[16],"suffer":[17],"from":[18,131],"training":[19,47,79],"stability":[20],"issues":[21,48],"and":[22,30,96,114],"in-correct":[23],"alignment":[24,99],"between":[25],"the":[26,31,46,51,63,78,88,98,116],"intermediate":[27],"acoustic":[28],"representation":[29],"text":[32],"input.":[33],"In":[34],"this":[35,69],"work,":[36],"we":[37,72],"propose":[38],"Regotron,":[39],"a":[40,82],"regularized":[41],"Tacotron2":[42],"version":[43],"which":[44,58],"alleviates":[45],"by":[49],"augmenting":[50],"objective":[52],"function":[53],"with":[54],"an":[55],"additional":[56,107],"term,":[57],"penalizes":[59],"non-monotonic":[60],"alignments":[61],"in":[62],"location-sensitive":[64],"attention":[65,84],"mechanism.":[66],"By":[67],"introducing":[68],"regularization":[70],"term":[71],"demonstrate":[73],"its":[74],"effectiveness":[75],"stabilize":[77],"process,":[80],"produce":[81],"monotonic":[83],"quicker":[85],"(13%":[86],"of":[87,91],"total":[89],"number":[90],"epochs":[92],"compared":[93],"Tacotron2)":[95],"reduce":[97],"errors":[100],"during":[101],"inference.":[102],"Moreover,":[103],"Regotron":[104],"has":[105],"minimal":[106],"computational":[108],"overhead,":[109],"reduces":[110],"common":[111],"TTS":[112],"mistakes":[113],"at":[115],"same":[117],"time":[118],"achieves":[119],"improved":[120],"naturalness":[122],"according":[123],"subjective":[125],"mean":[126],"opinion":[127],"scores":[128],"(MOS)":[129],"collected":[130],"50":[132],"evaluators.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}