{"id":"https://openalex.org/W4408353267","doi":"https://doi.org/10.1109/icassp49660.2025.10890428","title":"Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing","display_name":"Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353267","doi":"https://doi.org/10.1109/icassp49660.2025.10890428"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890428","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/A5092061330","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0001-8844-6418"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061001839","display_name":"Felix Stahlberg","orcid":"https://orcid.org/0000-0002-0430-5704"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Stahlberg","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101051347","display_name":"Shankar Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shankar Kumar","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092061330"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0203311,"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/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9887999892234802,"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":0.977400004863739,"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":0.7931170463562012},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.482021689414978},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38406604528427124},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33905160427093506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33364611864089966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931170463562012},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.482021689414978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38406604528427124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33905160427093506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33364611864089966}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890428","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W6678528935","https://openalex.org/W6682383452","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6794876948","https://openalex.org/W6796449527","https://openalex.org/W6801394596","https://openalex.org/W6810081322","https://openalex.org/W6847386241","https://openalex.org/W6849530321","https://openalex.org/W6850218400","https://openalex.org/W6851499912","https://openalex.org/W6852800892","https://openalex.org/W6857428954","https://openalex.org/W6859220857"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"excel":[4],"at":[5],"rewriting":[6,86,117],"tasks":[7],"such":[8],"as":[9],"text":[10],"style":[11],"transfer":[12],"and":[13,25,51,55,129,159],"grammatical":[14],"error":[15],"correction.":[16],"While":[17],"there":[18],"is":[19],"considerable":[20],"overlap":[21,47],"between":[22,48,154],"the":[23,30,40,46,49,52,65,115,120,137,142,151,155,160,169,174],"inputs":[24],"outputs":[26],"in":[27,84],"these":[28],"tasks,":[29],"decoding":[31],"cost":[32],"still":[33],"increases":[34],"with":[35,80,109],"output":[36,73],"length,":[37],"regardless":[38],"of":[39,42,77,122,150,168,173],"amount":[41],"overlap.":[43],"By":[44],"leveraging":[45],"input":[50],"output,":[53],"Kaneko":[54],"Okazaki":[56],"[1]":[57],"proposed":[58],"model-agnostic":[59],"edit":[60,94,134,156,175],"span":[61,111,157,176],"representations":[62,96,108],"to":[63,67,119],"compress":[64],"rewrites":[66],"save":[68],"computation.":[69],"They":[70],"reported":[71],"an":[72],"length":[74,170],"reduction":[75,171],"rate":[76,172],"nearly":[78],"80%":[79],"minimal":[81],"accuracy":[82],"impact":[83],"four":[85],"tasks.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91],"propose":[92],"alternative":[93],"phrase":[95],"inspired":[97],"by":[98],"phrase-based":[99],"statistical":[100],"machine":[101],"translation.":[102],"We":[103,113],"systematically":[104],"compare":[105],"our":[106,132,146],"phrasal":[107],"their":[110],"representations.":[112],"apply":[114],"LLM":[116],"model":[118,158,163],"task":[121],"Automatic":[123],"Speech":[124],"Recognition":[125],"(ASR)":[126],"post":[127],"editing":[128],"show":[130],"that":[131],"target-phrase-only":[133],"representation":[135],"has":[136],"best":[138],"efficiency-accuracy":[139],"trade-off.":[140],"On":[141],"LibriSpeech":[143],"test":[144],"set,":[145],"method":[147],"closes":[148],"50-60%":[149],"WER":[152],"gap":[153],"full":[161],"rewrite":[162],"while":[164],"losing":[165],"only":[166],"10-20%":[167],"model.":[177]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}