{"id":"https://openalex.org/W3185635705","doi":"https://doi.org/10.21437/interspeech.2021-286","title":"Detection and Analysis of Attention Errors in Sequence-to-Sequence Text-to-Speech","display_name":"Detection and Analysis of Attention Errors in Sequence-to-Sequence Text-to-Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3185635705","doi":"https://doi.org/10.21437/interspeech.2021-286","mag":"3185635705"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-286","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/218364594/Detection_and_analysis_VALENTINI_BOTINHAO_DOA02062021_AFV.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["The Centre for Speech Technology Research, The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, The University of Edinburgh","institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I4210159188","display_name":"SpeechTech (Czechia)","ror":"https://ror.org/05fsqes40","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159188"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CZ","GB"],"is_corresponding":true,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, The University of Edinburgh","institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062516688"],"corresponding_institution_ids":["https://openalex.org/I4210159188","https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2746","last_page":"2750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9988999962806702,"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":0.723736584186554},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6789762377738953},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5925620794296265},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.564914345741272},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.5459375381469727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5322427749633789},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.46158555150032043},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.4607445001602173},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4511331021785736},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.416338175535202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4106743335723877},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26352792978286743},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11448648571968079},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09749281406402588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723736584186554},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6789762377738953},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5925620794296265},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.564914345741272},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.5459375381469727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5322427749633789},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.46158555150032043},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.4607445001602173},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4511331021785736},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.416338175535202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4106743335723877},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26352792978286743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11448648571968079},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09749281406402588},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2021-286","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/97785425-9877-4edd-b524-78a5cd8bf6d8","is_oa":true,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2021/valentinibotinhao21_interspeech.html","pdf_url":"https://www.pure.ed.ac.uk/ws/files/218364594/Detection_and_analysis_VALENTINI_BOTINHAO_DOA02062021_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/97785425-9877-4edd-b524-78a5cd8bf6d8","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/97785425-9877-4edd-b524-78a5cd8bf6d8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Valentini-Botinhao, C & King, S 2021, Detection and analysis of attention errors in sequence-to-sequence text-to-speech. in Interspeech 2021. pp. 2746-2750, Interspeech 2021, Brno, Czech Republic, 30/08/21. https://doi.org/10.21437/Interspeech.2021-286","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/97785425-9877-4edd-b524-78a5cd8bf6d8","is_oa":true,"landing_page_url":"https://www.isca-speech.org/archive/interspeech_2021/valentinibotinhao21_interspeech.html","pdf_url":"https://www.pure.ed.ac.uk/ws/files/218364594/Detection_and_analysis_VALENTINI_BOTINHAO_DOA02062021_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3185635705.pdf","grobid_xml":"https://content.openalex.org/works/W3185635705.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1810943226","https://openalex.org/W2119929864","https://openalex.org/W2120847449","https://openalex.org/W2598638573","https://openalex.org/W2762464988","https://openalex.org/W2767052532","https://openalex.org/W2901997113","https://openalex.org/W2942807473","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972569067","https://openalex.org/W3015922793","https://openalex.org/W4298857617","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W2936002343","https://openalex.org/W172797710","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W168676510"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"speech":[1],"synthesis":[2],"models":[3],"are":[4,101],"notorious":[5],"for":[6,133],"gross":[7,99,135],"errors":[8,79,100,136,161],"such":[9,125],"as":[10,92,126],"skipping":[11],"and":[12,31,42,67,109,174],"repetition,":[13],"commonly":[14],"associated":[15],"with":[16,112,162],"failures":[17],"in":[18,106,110],"the":[19,62,76,131,139,146,154],"attention":[20,30,64,82,129],"mechanism.":[21],"While":[22],"a":[23,71,163],"lot":[24],"has":[25],"been":[26],"done":[27],"to":[28,104,138,159,172],"improve":[29],"decrease":[32],"errors,":[33],"this":[34,90],"paper":[35],"focuses":[36],"instead":[37],"on":[38,75],"automatic":[39],"error":[40,50,147],"detection":[41,51,148],"analysis.":[43],"We":[44,120],"evaluated":[45,155],"three":[46],"objective":[47],"metrics":[48,58,91,156],"against":[49],"scores":[52],"collected":[53],"by":[54],"human":[55],"listening.":[56],"All":[57],"were":[59,157],"derived":[60],"from":[61],"synthesised":[63],"matrix":[65],"alone":[66],"do":[68],"not":[69],"require":[70],"reference":[72],"signal,":[73],"relying":[74],"expectation":[77],"that":[78,98,115,123,151],"occur":[80,105],"when":[81],"is":[83],"dispersed":[84],"or":[85,118],"insufficient.":[86],"Using":[87],"one":[88],"of":[89,141,145,153,170],"an":[93],"analysis":[94],"tool,":[95],"we":[96],"observed":[97],"more":[102],"likely":[103],"longer":[107],"sentences":[108,111],"punctuation":[113],"marks":[114],"indicate":[116],"pause":[117],"break.":[119],"also":[121],"found":[122],"mechanisms":[124],"forcibly":[127],"incremented":[128],"have":[130],"potential":[132],"decreasing":[134],"but":[137],"detriment":[140],"naturalness.":[142],"The":[143],"results":[144],"evaluation":[149],"revealed":[150],"two":[152],"able":[158],"detect":[160],"relatively":[164],"high":[165],"success":[166],"rate,":[167],"obtaining":[168],"F-scores":[169],"up":[171],"0.89":[173],"0.96.<br/>":[175]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}