{"id":"https://openalex.org/W4392904003","doi":"https://doi.org/10.1109/icassp48485.2024.10448230","title":"Significant ASR Error Detection for Conversational Voice Assistants","display_name":"Significant ASR Error Detection for Conversational Voice Assistants","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904003","doi":"https://doi.org/10.1109/icassp48485.2024.10448230"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448230","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448230","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/A5078256928","display_name":"John Harvill","orcid":"https://orcid.org/0000-0003-3633-6756"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Harvill","raw_affiliation_strings":["University of Illinois Urbana-Champaign,USA","University of Illinois Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076711497","display_name":"Rinat Khaziev","orcid":"https://orcid.org/0000-0002-8566-3457"},"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":"Rinat Khaziev","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319184","display_name":"Scarlett Li","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":"Scarlett Li","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062316763","display_name":"Randy Cogill","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":"Randy Cogill","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100640128","display_name":"Lidan Wang","orcid":"https://orcid.org/0000-0003-0730-4202"},"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":"Lidan Wang","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063725454","display_name":"Gopinath Chennupati","orcid":"https://orcid.org/0000-0002-6223-8570"},"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":"Gopinath Chennupati","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000834101","display_name":"Hari Thadakamalla","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":"Hari Thadakamalla","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078256928"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.9797,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78181732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11606","last_page":"11610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.8319113850593567},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6528781652450562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6444551944732666},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6152646541595459},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5714151263237},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5554187297821045},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5176987648010254},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4584081470966339},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4518992602825165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40602385997772217},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09210428595542908},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0817270576953888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319113850593567},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6528781652450562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6444551944732666},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6152646541595459},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5714151263237},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5554187297821045},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5176987648010254},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4584081470966339},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4518992602825165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40602385997772217},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09210428595542908},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0817270576953888},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448230","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448230","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2168961642","https://openalex.org/W2938704169","https://openalex.org/W3016256870","https://openalex.org/W3036601975","https://openalex.org/W3046177490","https://openalex.org/W3093312917","https://openalex.org/W3156636935","https://openalex.org/W3168867926","https://openalex.org/W3209059054","https://openalex.org/W4205991051","https://openalex.org/W4221143046","https://openalex.org/W4285247752","https://openalex.org/W4287889156","https://openalex.org/W4385572941","https://openalex.org/W6761551260","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6809646742"],"related_works":["https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2047973478","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W2145649715","https://openalex.org/W2047313939","https://openalex.org/W2113666009","https://openalex.org/W2133478886","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Modern":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5,127],"are":[6,92],"evaluated":[7],"with":[8],"respect":[9],"to":[10,49,77,99,121],"Word":[11],"Error":[12],"Rate":[13],"(WER).":[14],"While":[15],"WER":[16],"is":[17,58,97],"a":[18,72,78,87],"useful":[19],"metric":[20],"for":[21,125],"training":[22],"and":[23,39,89],"evaluation":[24],"of":[25,54,81,86,115],"speech":[26],"models,":[27],"it":[28],"does":[29],"not":[30],"fully":[31],"reflect":[32],"the":[33,47,55,84,131],"difference":[34],"in":[35,106,109],"semantics":[36,85],"between":[37],"predicted":[38,88],"ground":[40],"truth":[41],"transcriptions.":[42],"In":[43,67],"conversational":[44,110],"voice":[45,111],"assistants,":[46],"ability":[48],"sufficiently":[50],"understand":[51],"semantic":[52],"meaning":[53],"user":[56],"request":[57],"often":[59],"more":[60],"important":[61],"than":[62],"recognizing":[63],"all":[64],"words":[65],"correctly.":[66],"this":[68],"work,":[69],"we":[70],"propose":[71],"system":[73],"that":[74,103],"can":[75,104,118],"determine,":[76],"high":[79],"degree":[80],"accuracy,":[82],"whether":[83],"reference":[90],"transcript":[91],"significantly":[93],"different.":[94],"This":[95],"knowledge":[96],"used":[98,120],"identify":[100],"ASR":[101,126],"errors":[102,117],"result":[105],"downstream":[107],"failure":[108],"assistants.":[112],"Reliable":[113],"identification":[114],"these":[116],"be":[119],"inform":[122],"design":[123],"choices":[124],"targeting":[128],"improvement":[129],"on":[130],"most":[132],"harmful":[133],"errors.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}