{"id":"https://openalex.org/W7130311988","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384906","title":"Stage-Wise Acoustic-Linguistic Fine-Tuning for Overlapped Speech Recognition: Does Ordering Matter?","display_name":"Stage-Wise Acoustic-Linguistic Fine-Tuning for Overlapped Speech Recognition: Does Ordering Matter?","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130311988","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384906"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11384906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126281656","display_name":"Saddam Annais Shaquille","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Saddam Annais Shaquille","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Puji Lestari","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9624999761581421,"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":0.9624999761581421,"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":0.007899999618530273,"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/T11309","display_name":"Music and Audio Processing","score":0.0071000000461936,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7343000173568726},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5593000054359436},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.545199990272522},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4198000133037567},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38420000672340393},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825000286102295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7343000173568726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6937999725341797},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45969998836517334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40059998631477356},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11384906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2460742184","https://openalex.org/W2962780374","https://openalex.org/W3013139777","https://openalex.org/W3081168214","https://openalex.org/W3154262773","https://openalex.org/W4406461489","https://openalex.org/W4408352078"],"related_works":[],"abstract_inverted_index":{"Recognizing":[0],"speech":[1],"when":[2,98,111],"multiple":[3],"individuals":[4],"speak":[5],"simultaneously":[6],"remains":[7],"a":[8,68,84,117,124],"significant":[9],"challenge":[10],"for":[11,133],"Automatic":[12],"Speech":[13],"Recognition":[14],"systems.":[15],"While":[16],"modern":[17],"architectures":[18],"integrating":[19],"audio":[20,49,100],"model":[21,25,46,50,77,101],"and":[22,122,130],"large":[23],"language":[24,45,76],"show":[26],"promise,":[27],"the":[28,44,48,57,64,75,80,93,99],"best":[29,58],"way":[30],"to":[31],"fine-tune":[32],"these":[33],"models":[34],"is":[35,67,102,108],"not":[36],"fully":[37],"explored.":[38],"This":[39,91,105],"study":[40],"investigates":[41],"whether":[42],"fine-tuning":[43,65,120],"first,":[47,51],"or":[52],"both":[53],"components":[54],"jointly":[55],"yields":[56],"results.":[59],"Our":[60],"results":[61,115],"demonstrate":[62],"that":[63],"order":[66],"critical":[69],"factor.":[70],"The":[71],"strategy":[72],"of":[73,88,119],"adapting":[74],"first":[78],"achieves":[79],"highest":[81],"performance":[82,106],"with":[83],"Word":[85],"Error":[86],"Rate":[87],"8.96":[89],"%.":[90],"surpasses":[92],"9.62":[94],"%":[95],"WER":[96],"obtained":[97],"trained":[103],"first.":[104],"advantage":[107],"also":[109],"apparent":[110],"using":[112],"LoRA.":[113],"These":[114],"establish":[116],"hierarchy":[118],"strategies":[121],"highlight":[123],"key":[125],"trade-off":[126],"between":[127],"transcription":[128],"accuracy":[129],"computational":[131],"efficiency":[132],"practical":[134],"applications.":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}
