{"id":"https://openalex.org/W4406461710","doi":"https://doi.org/10.1109/slt61566.2024.10832176","title":"Large Language Model Based Generative Error Correction: A Challenge and Baselines For Speech Recognition, Speaker Tagging, and Emotion Recognition","display_name":"Large Language Model Based Generative Error Correction: A Challenge and Baselines For Speech Recognition, Speaker Tagging, and Emotion Recognition","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461710","doi":"https://doi.org/10.1109/slt61566.2024.10832176"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511624","display_name":"Taejin Park","orcid":"https://orcid.org/0000-0003-2040-5884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taejin Park","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067285379","display_name":"Yuan Gong","orcid":"https://orcid.org/0000-0002-4537-0078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Gong","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930952","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0002-8688-5246"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuanchao Li","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012819966","display_name":"Yen\u2010Ting Lin","orcid":"https://orcid.org/0000-0001-7146-4687"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Ting Lin","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418547","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1957-6432"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100598749","display_name":"Yuchen Hu","orcid":"https://orcid.org/0009-0002-6789-2093"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073181369","display_name":"Kunal Dhawan","orcid":"https://orcid.org/0000-0002-5276-2475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunal Dhawan","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027052085","display_name":"Yun-Nung Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yun-Nung Chen","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["University of Palermo"],"affiliations":[{"raw_affiliation_string":"University of Palermo","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081337679","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0003-4415-7408"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011726172","display_name":"Catherine Lai","orcid":"https://orcid.org/0000-0001-8861-0281"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Catherine Lai","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114060825","display_name":"Andreas Stolcke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Uniphore"],"affiliations":[{"raw_affiliation_string":"Uniphore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":21,"corresponding_author_ids":["https://openalex.org/A5020376803"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4117,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90756191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.7954494953155518},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7453708648681641},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6342006921768188},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5910860300064087},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.556937575340271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537007212638855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5305633544921875},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5244655609130859},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4578581750392914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954494953155518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7453708648681641},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6342006921768188},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5910860300064087},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.556937575340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537007212638855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5305633544921875},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5244655609130859},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4578581750392914}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt61566.2024.10832176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/673128","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/673128","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1514944708","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1990005915","https://openalex.org/W1990387894","https://openalex.org/W2097560587","https://openalex.org/W2125336414","https://openalex.org/W2146334809","https://openalex.org/W2153013403","https://openalex.org/W2160451571","https://openalex.org/W2167241364","https://openalex.org/W2405472765","https://openalex.org/W2513383847","https://openalex.org/W2759071281","https://openalex.org/W2902864383","https://openalex.org/W2916997151","https://openalex.org/W2924677654","https://openalex.org/W2963227667","https://openalex.org/W2973127116","https://openalex.org/W2974231335","https://openalex.org/W3015686596","https://openalex.org/W3020336359","https://openalex.org/W3097263872","https://openalex.org/W3152221657","https://openalex.org/W3184326107","https://openalex.org/W3197947674","https://openalex.org/W3204618061","https://openalex.org/W3208480086","https://openalex.org/W4224308101","https://openalex.org/W4225890157","https://openalex.org/W4323066695","https://openalex.org/W4385570646","https://openalex.org/W4385822373","https://openalex.org/W4385822632","https://openalex.org/W4385822949","https://openalex.org/W4385823385","https://openalex.org/W4387158707","https://openalex.org/W4389315129","https://openalex.org/W4389520395","https://openalex.org/W4389520769","https://openalex.org/W4391021773","https://openalex.org/W4391021820","https://openalex.org/W4392902855","https://openalex.org/W4392903618","https://openalex.org/W4392904444","https://openalex.org/W4393178509","https://openalex.org/W4399511065","https://openalex.org/W4400070537","https://openalex.org/W4402112398","https://openalex.org/W4402667113","https://openalex.org/W4404782652","https://openalex.org/W4406461641","https://openalex.org/W4406461849","https://openalex.org/W6631362777","https://openalex.org/W6682421076","https://openalex.org/W6767671539","https://openalex.org/W6810081322","https://openalex.org/W6850218400","https://openalex.org/W6853925530","https://openalex.org/W6856423980","https://openalex.org/W6857131320","https://openalex.org/W6869385599"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Given":[0],"recent":[1],"advances":[2],"in":[3,38],"generative":[4,47],"AI":[5],"technology,":[6],"a":[7,26,88],"key":[8],"question":[9],"is":[10],"how":[11],"large":[12],"language":[13,39,59,95],"models":[14,96],"(LLMs)":[15],"can":[16],"enhance":[17],"acoustic":[18],"modeling":[19,40,60],"tasks":[20,74],"using":[21],"text":[22],"decoding":[23],"results":[24],"from":[25,104],"frozen,":[27],"pretrained":[28,94],"automatic":[29],"speech":[30,42,48],"recognition":[31],"(ASR)":[32],"model.":[33],"To":[34],"explore":[35],"new":[36],"capabilities":[37],"for":[41,112],"processing,":[43],"we":[44],"introduce":[45],"the":[46],"transcription":[49,64],"error":[50],"correction":[51],"(GenSEC)":[52],"challenge.":[53],"This":[54],"challenge":[55],"comprises":[56],"three":[57],"post-ASR":[58,63],"tasks:":[61],"(i)":[62],"correction,":[65],"(ii)":[66],"speaker":[67],"tagging,":[68],"and":[69],"(iii)":[70],"emotion":[71],"recognition.":[72],"These":[73],"aim":[75],"to":[76,87],"emulate":[77],"future":[78,114],"LLM-based":[79],"agents":[80],"handling":[81],"voice-based":[82],"interfaces":[83],"while":[84],"remaining":[85],"accessible":[86],"broad":[89],"audience":[90],"by":[91],"utilizing":[92],"open":[93],"or":[97],"agent-based":[98],"APIs.":[99],"We":[100],"also":[101],"discuss":[102],"insights":[103],"baseline":[105],"evaluations,":[106],"as":[107,109],"well":[108],"lessons":[110],"learned":[111],"designing":[113],"evaluations.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}