{"id":"https://openalex.org/W4392903942","doi":"https://doi.org/10.1109/icassp48485.2024.10447164","title":"Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition","display_name":"Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903942","doi":"https://doi.org/10.1109/icassp48485.2024.10447164"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447164","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5104260047","display_name":"David M. Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M. Chan","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley","Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102095407","display_name":"Shalini Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shalini Ghosh","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065684433","display_name":"Hitesh Tulsiani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hitesh Tulsiani","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012163532","display_name":"Bj\u00f6rn Hoffmeister","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Hoffmeister","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02530708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11806","last_page":"11810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","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":0.9991999864578247,"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":0.832267165184021},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7450239062309265},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5993005633354187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.59465491771698},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5320758819580078},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5181370973587036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48031800985336304},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4584606885910034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832267165184021},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7450239062309265},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5993005633354187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.59465491771698},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5320758819580078},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5181370973587036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48031800985336304},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4584606885910034},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447164","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/W2251058040","https://openalex.org/W2886025712","https://openalex.org/W2962767983","https://openalex.org/W2963491014","https://openalex.org/W2964006684","https://openalex.org/W2973172693","https://openalex.org/W2974231335","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3148654612","https://openalex.org/W3156555225","https://openalex.org/W3160799772","https://openalex.org/W3205715971","https://openalex.org/W3209721572","https://openalex.org/W3214803981","https://openalex.org/W4210673375","https://openalex.org/W4221146627","https://openalex.org/W4224918838","https://openalex.org/W4225985539","https://openalex.org/W4226420874","https://openalex.org/W4287812705","https://openalex.org/W4297841871","https://openalex.org/W4313703382","https://openalex.org/W4372347360","https://openalex.org/W4372349774","https://openalex.org/W4377865080","https://openalex.org/W4386058713","https://openalex.org/W4389010490","https://openalex.org/W6754637164","https://openalex.org/W6761205521","https://openalex.org/W6767671539","https://openalex.org/W6771467084","https://openalex.org/W6776700526","https://openalex.org/W6780218876","https://openalex.org/W6803544266","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6849128116","https://openalex.org/W6852997429"],"related_works":["https://openalex.org/W3201126466","https://openalex.org/W4282827391","https://openalex.org/W4386828785","https://openalex.org/W1569283511","https://openalex.org/W3165580226","https://openalex.org/W3135401135","https://openalex.org/W2886688859","https://openalex.org/W4236193183","https://openalex.org/W3133164560","https://openalex.org/W2296205523"],"abstract_inverted_index":{"While":[0],"word":[1],"error":[2],"rates":[3],"of":[4,21,28,41,72,77,85,100,106,117],"automatic":[5],"speech":[6,32],"recognition":[7,33],"(ASR)":[8],"systems":[9,23,37,47,130],"have":[10],"consistently":[11],"fallen,":[12],"natural":[13],"language":[14],"understanding":[15],"(NLU)":[16],"applications":[17],"built":[18],"on":[19,109],"top":[20],"ASR":[22,107],"still":[24],"attribute":[25],"significant":[26],"numbers":[27,40],"failures":[29],"to":[30,50,123,128,140,145],"low-quality":[31],"results.":[34],"Existing":[35],"assistant":[36],"collect":[38],"large":[39],"these":[42,46,53],"unsuccessful":[43,90],"interactions,":[44,54],"but":[45],"usually":[48],"fail":[49],"learn":[51],"from":[52],"even":[55],"in":[56,79,89],"an":[57],"offline":[58],"fashion.":[59],"In":[60],"this":[61],"work,":[62],"we":[63,134],"introduce":[64],"CLC:":[65],"Contrastive":[66],"Learning":[67],"for":[68,74],"Conversations,":[69],"a":[70,80,111],"family":[71,99],"methods":[73],"contrastive":[75],"fine-tuning":[76],"models":[78,108],"self-supervised":[81],"fashion,":[82],"making":[83],"use":[84],"easily":[86],"detectable":[87],"artifacts":[88],"conversations":[91],"with":[92],"assistants.":[93],"We":[94],"demonstrate":[95],"that":[96,136],"our":[97],"CLC":[98,137],"approaches":[101],"can":[102,138],"improve":[103,141],"the":[104],"performance":[105,142],"OD3,":[110],"new":[112],"public":[113],"large-scale":[114],"semi-synthetic":[115],"meta-dataset":[116],"audio":[118],"task-oriented":[119],"dialogues,":[120],"by":[121,143],"up":[122,144],"19.2%.":[124],"These":[125],"gains":[126],"transfer":[127],"real-world":[129],"as":[131],"well,":[132],"where":[133],"show":[135],"help":[139],"6.7%":[146],"over":[147],"baselines.<sup":[148],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[150]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}