{"id":"https://openalex.org/W4391021750","doi":"https://doi.org/10.1109/asru57964.2023.10389657","title":"Generalized Zero-Shot Audio-to-Intent Classification","display_name":"Generalized Zero-Shot Audio-to-Intent Classification","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021750","doi":"https://doi.org/10.1109/asru57964.2023.10389657"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5093219929","display_name":"Veera Raghavendra Elluru","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Veera Raghavendra Elluru","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065734653","display_name":"Devang Kulshreshtha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devang Kulshreshtha","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052189588","display_name":"Rohit Paturi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Paturi","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050552820","display_name":"Sravan Bodapati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sravan Bodapati","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004616142","display_name":"Srikanth Ronanki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srikanth Ronanki","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093219929"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4135,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6057822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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":0.9966999888420105,"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":0.7589138746261597},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7524083852767944},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5779827833175659},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5515576601028442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5430251359939575},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5002472400665283},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.49940013885498047},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.48861390352249146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.442211389541626},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.42991313338279724},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4137047529220581},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3460972309112549},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30323973298072815},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07112231850624084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589138746261597},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7524083852767944},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5779827833175659},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5515576601028442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430251359939575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5002472400665283},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.49940013885498047},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.48861390352249146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.442211389541626},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.42991313338279724},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4137047529220581},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3460972309112549},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30323973298072815},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07112231850624084},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1992753948","https://openalex.org/W2150295085","https://openalex.org/W2713640100","https://openalex.org/W2797583228","https://openalex.org/W2872172641","https://openalex.org/W2887567284","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2930959424","https://openalex.org/W2963486920","https://openalex.org/W2973049979","https://openalex.org/W3016473712","https://openalex.org/W3100460087","https://openalex.org/W3127686677","https://openalex.org/W3138521398","https://openalex.org/W3155705048","https://openalex.org/W3160016036","https://openalex.org/W3161223924","https://openalex.org/W3171926364","https://openalex.org/W3197580070","https://openalex.org/W3197900814","https://openalex.org/W3209059054","https://openalex.org/W3211196264","https://openalex.org/W3211224152","https://openalex.org/W3215155711","https://openalex.org/W4224932952","https://openalex.org/W4312685284","https://openalex.org/W4319862265","https://openalex.org/W4372266552","https://openalex.org/W4385245566","https://openalex.org/W4385567350","https://openalex.org/W4385822467","https://openalex.org/W6682222085","https://openalex.org/W6739901393","https://openalex.org/W6746524570","https://openalex.org/W6750665317","https://openalex.org/W6753441104","https://openalex.org/W6755207826","https://openalex.org/W6776148200","https://openalex.org/W6789826613","https://openalex.org/W6791353385","https://openalex.org/W6803378298","https://openalex.org/W6981026971"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W4287812790","https://openalex.org/W3017861469","https://openalex.org/W3035597485","https://openalex.org/W3213312935","https://openalex.org/W3201396246"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"understanding":[2],"systems":[3],"using":[4,80],"audio-only":[5,133],"data":[6],"are":[7],"gaining":[8],"popularity,":[9],"yet":[10],"their":[11],"ability":[12],"to":[13,64,98,132],"handle":[14],"unseen":[15,78,114],"intents":[16,79,115],"remains":[17],"limited.":[18],"In":[19],"this":[20],"study,":[21],"we":[22,42],"propose":[23,85],"a":[24,32,45,53,60,86],"generalized":[25,74],"zero-shot":[26,75,100,110],"audio-to-intent":[27,47],"classification":[28,76,112],"framework":[29],"with":[30],"only":[31],"few":[33],"sample":[34,69],"text":[35,70],"sentences":[36],"per":[37],"intent.":[38],"To":[39],"achieve":[40],"this,":[41],"first":[43],"train":[44],"supervised":[46],"classifier":[48],"by":[49,118],"making":[50],"use":[51],"of":[52,109,116],"self-supervised":[54],"pre-trained":[55],"model.":[56],"We":[57,83],"then":[58],"leverage":[59],"neural":[61],"audio":[62,66,96],"synthesizer":[63],"create":[65],"embeddings":[67],"for":[68,122],"utterances":[71],"and":[72,120,125],"perform":[73],"on":[77,113],"cosine":[81],"similarity.":[82],"also":[84],"multimodal":[87,103],"training":[88,104],"strategy":[89],"that":[90],"incorporates":[91],"lexical":[92],"information":[93],"into":[94],"the":[95,107,123],"representation":[97],"improve":[99],"performance.":[101],"Our":[102],"approach":[105],"improves":[106],"accuracy":[108],"intent":[111],"SLURP":[117,124],"2.75%":[119],"18.2%":[121],"internal":[126],"goal-oriented":[127],"dialog":[128],"datasets,":[129],"respectively,":[130],"compared":[131],"training.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}