{"id":"https://openalex.org/W4402112398","doi":"https://doi.org/10.21437/interspeech.2024-209","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","display_name":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112398","doi":"https://doi.org/10.21437/interspeech.2024-209"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-209","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-209","pdf_url":"https://www.isca-archive.org/interspeech_2024/wang24h_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/wang24h_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108047863","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-5483-0243"},"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":"Quan Wang","raw_affiliation_strings":["Google LLC , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC , USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103123086","display_name":"Yiling Huang","orcid":"https://orcid.org/0009-0008-0554-0942"},"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":"Yiling Huang","raw_affiliation_strings":["Google LLC , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC , USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078020198","display_name":"Guanlong Zhao","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":"Guanlong Zhao","raw_affiliation_strings":["Google LLC , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC , USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055308740","display_name":"Evan B. Clark","orcid":"https://orcid.org/0000-0002-6242-5413"},"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":"Evan Clark","raw_affiliation_strings":["Google LLC , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC , USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654154","display_name":"Wei Xia","orcid":"https://orcid.org/0000-0003-3157-6988"},"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":"Wei Xia","raw_affiliation_strings":["Google LLC , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC , USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","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":"Hank Liao","raw_affiliation_strings":["Google LLC , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC , USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4148,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97035954,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3754","last_page":"3758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9925000071525574,"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":0.9925000071525574,"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":0.9742000102996826,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7892317771911621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7708377838134766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5608564019203186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5343189835548401},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4080171287059784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3564258813858032}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7892317771911621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708377838134766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5608564019203186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5343189835548401},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4080171287059784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3564258813858032}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-209","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-209","pdf_url":"https://www.isca-archive.org/interspeech_2024/wang24h_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-209","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-209","pdf_url":"https://www.isca-archive.org/interspeech_2024/wang24h_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112398.pdf","grobid_xml":"https://content.openalex.org/works/W4402112398.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"this":[1,23,74],"paper,":[2],"we":[3],"introduce":[4],"DiarizationLM,":[5],"a":[6,19,40,71,95],"framework":[7,75],"to":[8,14,50,80],"leverage":[9],"large":[10],"language":[11],"models":[12],"(LLM)":[13],"post-process":[15],"the":[16,25,28,48,57,63,68,102,107,115],"outputs":[17,26,55],"from":[18],"speaker":[20,34,85],"diarization":[21,35,65,86],"system.In":[22],"framework,":[24],"of":[27,56],"automatic":[29],"speech":[30],"recognition":[31],"(ASR)":[32],"and":[33,84,112],"systems":[36,87],"are":[37],"represented":[38],"as":[39,62],"compact":[41],"textual":[42],"format,":[43],"which":[44],"is":[45],"included":[46],"in":[47],"prompt":[49],"an":[51],"optionally":[52],"finetuned":[53,96],"LLM.The":[54],"LLM":[58],"can":[59,76,100],"be":[60,77],"used":[61],"refined":[64],"results":[66],"with":[67],"desired":[69],"enhancement.As":[70],"post-processing":[72],"step,":[73],"easily":[78],"applied":[79],"any":[81],"off-the-shelf":[82],"ASR":[83],"without":[88],"retraining":[89],"existing":[90],"components.Our":[91],"experiments":[92],"show":[93],"that":[94],"PaLM":[97],"2-S":[98],"model":[99],"reduce":[101],"WDER":[103],"by":[104],"rel.55.5%":[105],"on":[106,114],"Fisher":[108],"telephone":[109],"conversation":[110],"dataset,":[111],"rel.44.9%":[113],"Callhome":[116],"English":[117],"dataset.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}