{"id":"https://openalex.org/W4408353547","doi":"https://doi.org/10.1109/icassp49660.2025.10890148","title":"SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models","display_name":"SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353547","doi":"https://doi.org/10.1109/icassp49660.2025.10890148"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5066528816","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-9621-9888"},"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":true,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"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/A5034455276","display_name":"Amber Afshan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amber Afshan","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047128701","display_name":"Sundararajan Srinivasan","orcid":"https://orcid.org/0000-0002-3387-9889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sundararajan Srinivasan","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066528816"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0204154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.965499997138977,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9302999973297119,"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":0.7331492900848389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6036831140518188},{"id":"https://openalex.org/keywords/seal","display_name":"Seal (emblem)","score":0.546347439289093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3645789623260498},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3263639211654663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3237878084182739},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.055777400732040405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331492900848389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6036831140518188},{"id":"https://openalex.org/C2777755289","wikidata":"https://www.wikidata.org/wiki/Q162919","display_name":"Seal (emblem)","level":2,"score":0.546347439289093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3645789623260498},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3263639211654663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3237878084182739},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.055777400732040405},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2962788625","https://openalex.org/W2963227667","https://openalex.org/W2973127116","https://openalex.org/W2981857663","https://openalex.org/W3008357631","https://openalex.org/W3020336359","https://openalex.org/W3097777922","https://openalex.org/W3143367551","https://openalex.org/W3162847598","https://openalex.org/W3163842642","https://openalex.org/W3163903701","https://openalex.org/W3203417382","https://openalex.org/W4226491018","https://openalex.org/W4297841514","https://openalex.org/W4375869348","https://openalex.org/W4385572162","https://openalex.org/W4385822373","https://openalex.org/W4385822816","https://openalex.org/W4385823501","https://openalex.org/W4389520385","https://openalex.org/W4391021542","https://openalex.org/W4392902855","https://openalex.org/W4402111555","https://openalex.org/W4402111958","https://openalex.org/W4402112398","https://openalex.org/W4408350568","https://openalex.org/W6809874571","https://openalex.org/W6846909052","https://openalex.org/W6847363464","https://openalex.org/W6853251322","https://openalex.org/W6854874810","https://openalex.org/W6858023062","https://openalex.org/W6861275358","https://openalex.org/W6866575372"],"related_works":["https://openalex.org/W4237333278","https://openalex.org/W2461810893","https://openalex.org/W4200519391","https://openalex.org/W2326160135","https://openalex.org/W2388266094","https://openalex.org/W2362428907","https://openalex.org/W2349717903","https://openalex.org/W4245309835","https://openalex.org/W753070179","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Speaker":[0],"Diarization":[1],"(SD)":[2],"is":[3],"a":[4,50,68,89],"crucial":[5],"component":[6],"of":[7,22],"modern":[8],"end-to-end":[9],"ASR":[10],"pipelines.":[11],"Traditional":[12],"SD":[13],"systems,":[14],"which":[15],"are":[16],"typically":[17],"audio-based":[18],"and":[19,32,114],"operate":[20],"independently":[21],"ASR,":[23],"often":[24],"introduce":[25,67],"speaker":[26,30,52,106],"errors,":[27],"particularly":[28],"during":[29],"transitions":[31],"overlapping":[33],"speech.":[34],"Recently,":[35],"language":[36,41],"models":[37,42],"including":[38],"fine-tuned":[39],"large":[40],"(LLMs)":[43],"have":[44],"shown":[45],"to":[46,73,82,118],"be":[47],"effective":[48],"as":[49],"second-pass":[51],"error":[53,107],"corrector":[54],"by":[55,109],"leveraging":[56],"lexical":[57],"context":[58],"in":[59],"the":[60,79,83,105,119],"transcribed":[61],"output.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"novel":[69],"acoustic":[70,80],"conditioning":[71],"approach":[72,102],"provide":[74],"more":[75],"fine-grained":[76],"information":[77],"from":[78],"diarizer":[81],"LLM.":[84],"We":[85],"also":[86],"show":[87],"that":[88],"simpler":[90],"constrained":[91],"decoding":[92],"strategy":[93],"reduces":[94,104],"LLM":[95],"hallucinations,":[96],"while":[97],"avoiding":[98],"complicated":[99],"post-processing.":[100],"Our":[101],"significantly":[103],"rates":[108],"24-43%":[110],"across":[111],"Fisher,":[112],"Callhome,":[113],"RT03-CTS":[115],"datasets,":[116],"compared":[117],"first-pass":[120],"Acoustic":[121],"SD.":[122]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}