{"id":"https://openalex.org/W3137608412","doi":"https://doi.org/10.1109/taslp.2022.3145313","title":"Hallucination of Speech Recognition Errors With Sequence to Sequence Learning","display_name":"Hallucination of Speech Recognition Errors With Sequence to Sequence Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3137608412","doi":"https://doi.org/10.1109/taslp.2022.3145313","mag":"3137608412"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3145313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3145313","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.12258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070013411","display_name":"Prashant Serai","orcid":"https://orcid.org/0000-0002-4672-4413"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Serai","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Ohio State University"],"raw_orcid":"https://orcid.org/0000-0002-4672-4413","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113145191","display_name":"Vishal Sunder","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal Sunder","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Ohio State University"],"raw_orcid":"https://orcid.org/0000-0001-8004-5169","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.2319,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56986239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"890","last_page":"900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.7931780815124512},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7369775772094727},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5786076784133911},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.554092526435852},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5482838153839111},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.5395973920822144},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5052888989448547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4930209815502167},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43842920660972595},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42356258630752563},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4209112823009491},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10367229580879211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931780815124512},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7369775772094727},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5786076784133911},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.554092526435852},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5482838153839111},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.5395973920822144},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5052888989448547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4930209815502167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43842920660972595},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42356258630752563},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4209112823009491},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10367229580879211},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2022.3145313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3145313","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2103.12258","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.12258","pdf_url":"https://arxiv.org/pdf/2103.12258","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3137608412","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.12258","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.12258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.12258","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.12258","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.12258","pdf_url":"https://arxiv.org/pdf/2103.12258","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6786997593","display_name":null,"funder_award_id":"1618336","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W21963070","https://openalex.org/W97072897","https://openalex.org/W99561634","https://openalex.org/W104184427","https://openalex.org/W168280322","https://openalex.org/W399167303","https://openalex.org/W1522301498","https://openalex.org/W1980280616","https://openalex.org/W1993607814","https://openalex.org/W2121642367","https://openalex.org/W2130942839","https://openalex.org/W2131342762","https://openalex.org/W2148182949","https://openalex.org/W2166637769","https://openalex.org/W2194775991","https://openalex.org/W2402827806","https://openalex.org/W2785918467","https://openalex.org/W2829536104","https://openalex.org/W2933138175","https://openalex.org/W2936399153","https://openalex.org/W2938630833","https://openalex.org/W2963386218","https://openalex.org/W2963403868","https://openalex.org/W2964265128","https://openalex.org/W2971296908","https://openalex.org/W3016053077","https://openalex.org/W3016256870","https://openalex.org/W3035349600","https://openalex.org/W3049038774","https://openalex.org/W3105804405","https://openalex.org/W3147670539","https://openalex.org/W6603931906","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6735377749","https://openalex.org/W6737778391","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2215111428","https://openalex.org/W3011026370","https://openalex.org/W3207836786","https://openalex.org/W2402827806","https://openalex.org/W2919666548","https://openalex.org/W2901265786","https://openalex.org/W2404544250","https://openalex.org/W2152638814","https://openalex.org/W2216696018","https://openalex.org/W2171026889","https://openalex.org/W2125247927","https://openalex.org/W2916997151","https://openalex.org/W2041670430","https://openalex.org/W2165280259","https://openalex.org/W1546388417","https://openalex.org/W35700928","https://openalex.org/W3204996224","https://openalex.org/W2884483159","https://openalex.org/W1525797625","https://openalex.org/W139927782"],"abstract_inverted_index":{"Prior":[0],"work":[1],"in":[2,138],"this":[3],"domain":[4],"has":[5],"focused":[6],"on":[7,45],"modeling":[8],"errors":[9,65,120,137],"at":[10,151],"the":[11,20,100,108,112],"phonetic":[12],"level,":[13],"while":[14,89],"using":[15],"a":[16,53,125,139],"lexicon":[17],"to":[18,22,36,121,134],"convert":[19],"phones":[21],"words,":[23],"usually":[24],"accompanied":[25],"by":[26],"an":[27,46,67,78,86,92],"FST":[28],"Language":[29],"model.":[30],"We":[31],"present":[32],"novel":[33],"end-to-end":[34],"models":[35],"directly":[37],"predict":[38],"hallucinated":[39,118],"ASR":[40,69,80,102,119,136],"word":[41,48],"sequence":[42,49],"outputs,":[43],"conditioning":[44],"input":[47],"as":[50,52,75,77],"well":[51,76],"corresponding":[54],"phoneme":[55],"sequence.":[56],"This":[57],"improves":[58],"prior":[59],"published":[60],"results":[61],"for":[62,124],"recall":[63],"of":[64,72,83,111],"from":[66,85,99],"in-domain":[68],"system\u2019s":[70,81],"transcription":[71],"unseen":[73],"data,":[74],"out-of-domain":[79],"transcriptions":[82],"audio":[84,148],"unrelated":[87],"task,":[88,141],"additionally":[90],"exploring":[91],"in-between":[93],"scenario":[94],"when":[95,142],"limited":[96],"characterization":[97],"data":[98],"test":[101],"system":[103],"is":[104],"obtainable.":[105],"To":[106],"verify":[107],"extrinsic":[109],"validity":[110],"method,":[113],"we":[114],"also":[115],"use":[116],"our":[117],"augment":[122],"training":[123],"spoken":[126],"question":[127],"classifier,":[128],"finding":[129],"that":[130],"they":[131],"enable":[132],"robustness":[133],"real":[135],"downstream":[140],"scarce":[143],"or":[144],"even":[145],"zero":[146],"task-specific":[147],"was":[149],"available":[150],"train-time.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2022-07-25T00:00:00"}