{"id":"https://openalex.org/W7148616372","doi":"https://doi.org/10.1109/asru65441.2025.11434801","title":"Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition","display_name":"Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148616372","doi":"https://doi.org/10.1109/asru65441.2025.11434801"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132818311","display_name":"Hao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Shi","raw_affiliation_strings":["SB Intuitions,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SB Intuitions,Tokyo,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["SB Intuitions,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SB Intuitions,Tokyo,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008935760","display_name":"Tomoya Mizumoto","orcid":null},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomoya Mizumoto","raw_affiliation_strings":["SB Intuitions,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SB Intuitions,Tokyo,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069958697","display_name":"Lianbo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lianbo Liu","raw_affiliation_strings":["SB Intuitions,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SB Intuitions,Tokyo,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115912838","display_name":"Atsushi Kojima","orcid":null},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atsushi Kojima","raw_affiliation_strings":["SB Intuitions,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SB Intuitions,Tokyo,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["SB Intuitions,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"SB Intuitions,Tokyo,Japan","institution_ids":["https://openalex.org/I88773910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132818311"],"corresponding_institution_ids":["https://openalex.org/I88773910"],"apc_list":null,"apc_paid":null,"fwci":4.3637,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95469165,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9218000173568726,"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":0.9218000173568726,"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":0.023800000548362732,"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/T10863","display_name":"Voice and Speech Disorders","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5842999815940857},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5371999740600586},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5360999703407288},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4896000027656555},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44279998540878296},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.40549999475479126},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3386000096797943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814000248908997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6736000180244446},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5371999740600586},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44279998540878296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3418999910354614},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2035576074","https://openalex.org/W2255466643","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2890244912","https://openalex.org/W2962866211","https://openalex.org/W2963574857","https://openalex.org/W2972541922","https://openalex.org/W3013139777","https://openalex.org/W3015746570","https://openalex.org/W3034999214","https://openalex.org/W3198522318","https://openalex.org/W3209984917","https://openalex.org/W4297841499","https://openalex.org/W4319586290","https://openalex.org/W4372342485","https://openalex.org/W4372349800","https://openalex.org/W4375869385","https://openalex.org/W4391021760","https://openalex.org/W4392904327","https://openalex.org/W4399168695","https://openalex.org/W4402112405","https://openalex.org/W4402116593","https://openalex.org/W4404781855","https://openalex.org/W4406461489","https://openalex.org/W4406461710","https://openalex.org/W4406461869","https://openalex.org/W4408352078","https://openalex.org/W4408355506"],"related_works":[],"abstract_inverted_index":{"Prompts":[0],"are":[1,80],"crucial":[2],"for":[3,7,109],"task":[4],"definition":[5],"and":[6,58,73,88,144,191],"improving":[8],"the":[9,41,61,83,93,102,115,124,150,156,163,178],"performance":[10,69,187],"of":[11,43,134],"large":[12],"language":[13],"models":[14],"(LLM)-based":[15],"systems.":[16],"However,":[17],"existing":[18],"LLM-based":[19,157],"multi-talker":[20],"(MT)":[21],"automatic":[22],"speech":[23,84,95,141],"recognition":[24],"(ASR)":[25],"systems":[26],"either":[27],"omit":[28],"prompts":[29,44,56,65],"or":[30],"rely":[31],"on":[32,149],"simple":[33],"task-definition":[34],"prompts,":[35],"with":[36],"no":[37],"prior":[38],"work":[39],"exploring":[40],"design":[42,128],"to":[45,66,86,168],"enhance":[46],"performance.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,127],"propose":[52],"extracting":[53],"serialized":[54,74,116,135,140],"output":[55,136],"(SOP)":[57],"explicitly":[59],"guiding":[60],"LLM":[62],"using":[63,119],"structured":[64],"improve":[67],"system":[68],"(SOP-MT-ASR).":[70],"A":[71],"Separator":[72],"Connectionist":[75],"Temporal":[76],"Classification":[77],"(CTC)":[78],"layers":[79],"inserted":[81],"after":[82],"encoder":[85],"separate":[87],"extract":[89],"MT":[90],"content":[91],"from":[92],"mixed":[94],"encoding":[96],"in":[97,162],"a":[98,107,129],"first-speaking-first-out":[99],"manner.":[100],"Subsequently,":[101],"SOP,":[103],"which":[104],"serves":[105],"as":[106,177],"prompt":[108],"LLMs,":[110],"is":[111],"obtained":[112],"by":[113],"decoding":[114],"CTC":[117],"outputs":[118],"greedy":[120],"search.":[121],"To":[122],"train":[123],"model":[125,159],"effectively,":[126],"threestage":[130],"training":[131,137],"strategy,":[132],"consisting":[133],"(SOT)":[138],"fine-tuning,":[139],"information":[142],"extraction,":[143],"SOP-based":[145],"adaptation.":[146],"Experimental":[147],"results":[148],"LibriMix":[151],"dataset":[152],"show":[153],"that,":[154],"although":[155],"SOT":[158],"performs":[160],"well":[161],"two-talker":[164],"scenario,":[165],"it":[166],"fails":[167],"fully":[169],"leverage":[170],"LLMs":[171],"under":[172,188],"more":[173],"complex":[174],"conditions,":[175],"such":[176],"three-talker":[179,192],"scenario.":[180],"The":[181],"proposed":[182],"SOP":[183],"approach":[184],"significantly":[185],"improved":[186],"both":[189],"two-":[190],"conditions.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}