{"id":"https://openalex.org/W3095187499","doi":"https://doi.org/10.21437/interspeech.2020-1062","title":"End-to-End Speech-to-Dialog-Act Recognition","display_name":"End-to-End Speech-to-Dialog-Act Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095187499","doi":"https://doi.org/10.21437/interspeech.2020-1062","mag":"3095187499"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1062","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073047124","display_name":"Viet-Trung Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Viet-Trung Dang","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048297544","display_name":"Tianyu Zhao","orcid":"https://orcid.org/0000-0003-2401-4098"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tianyu Zhao","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103835523","display_name":"Sei Ueno","orcid":"https://orcid.org/0000-0002-2255-3154"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sei Ueno","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3910","last_page":"3914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9986000061035156,"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/dialog-box","display_name":"Dialog box","score":0.7612950801849365},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7247538566589355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6800012588500977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5919987559318542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31464603543281555},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15173569321632385}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7612950801849365},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7247538566589355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6800012588500977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5919987559318542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31464603543281555},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15173569321632385}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1062","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W27394811","https://openalex.org/W854541894","https://openalex.org/W1586532344","https://openalex.org/W2007261869","https://openalex.org/W2112078429","https://openalex.org/W2128970689","https://openalex.org/W2136487259","https://openalex.org/W2146785422","https://openalex.org/W2327501763","https://openalex.org/W2406881692","https://openalex.org/W2517028602","https://openalex.org/W2597757402","https://openalex.org/W2774605568","https://openalex.org/W2800921391","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2962826786","https://openalex.org/W2963288440","https://openalex.org/W2964139507","https://openalex.org/W2972327934","https://openalex.org/W2972584841"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W2939790162"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"understanding,":[2],"which":[3,39,92],"extracts":[4],"intents":[5,43],"and/or":[6],"semantic":[7],"concepts":[8],"in":[9,107],"utterances,":[10],"is":[11,21,77,105,123],"conventionally":[12],"formulated":[13],"as":[14,115,117],"a":[15,94],"post-processing":[16],"of":[17,97],"automatic":[18],"speech":[19,60],"recognition.It":[20],"usually":[22],"trained":[23],"with":[24,31,42,47,79,131],"oracle":[25],"transcripts,":[26],"but":[27,44],"needs":[28],"to":[29,126],"deal":[30],"errors":[32],"by":[33],"ASR.Moreover,":[34],"there":[35],"are":[36,40],"acoustic":[37],"features":[38],"related":[41],"not":[45],"represented":[46],"the":[48,65,69,72,89,102,132,137,147],"transcripts.In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"an":[54,80,108],"end-to-end":[55,109],"model":[56,83,122],"that":[57,136],"directly":[58],"converts":[59],"into":[61],"dialog":[62,73,142],"acts":[63],"without":[64],"deterministic":[66],"transcription":[67],"process.In":[68],"proposed":[70,138],"model,":[71],"act":[74,143],"recognition":[75,144],"network":[76,104],"conjunct":[78],"acoustic-to-word":[81],"ASR":[82,99,120],"at":[84],"its":[85],"latent":[86],"layer":[87],"before":[88],"softmax":[90],"layer,":[91],"provides":[93],"distributed":[95],"representation":[96],"word-level":[98],"decoding":[100],"information.Then,":[101],"entire":[103],"fine-tuned":[106],"manner.This":[110],"allows":[111],"for":[112],"stable":[113],"training":[114],"well":[116],"robustness":[118],"against":[119],"errors.The":[121],"further":[124],"extended":[125],"conduct":[127],"DA":[128],"segmentation":[129],"jointly.Evaluations":[130],"Switchboard":[133],"corpus":[134],"demonstrate":[135],"method":[139],"significantly":[140],"improves":[141],"accuracy":[145],"from":[146],"conventional":[148],"pipeline":[149],"framework.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}