{"id":"https://openalex.org/W7225199769","doi":"https://doi.org/10.21437/interspeech.2026-2441","title":"Parameter-Efficient Adaptation of Speech-Aware LLMs for Timestamp Prediction","display_name":"Parameter-Efficient Adaptation of Speech-Aware LLMs for Timestamp Prediction","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7225199769","doi":"https://doi.org/10.21437/interspeech.2026-2441"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2026-2441","doi":"https://doi.org/10.21437/interspeech.2026-2441","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-2441","pdf_url":"https://www.isca-archive.org/interspeech_2026/sunder26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.isca-archive.org/interspeech_2026/sunder26_interspeech.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113145191","display_name":"Vishal Sunder","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishal Sunder","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620","observed_orcids":["https://orcid.org/0000-0001-7573-0620"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086248084","display_name":"Xulin Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xulin Fan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian E. D. Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837","observed_orcids":["https://orcid.org/0000-0002-1343-6837"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009","observed_orcids":["https://orcid.org/0009-0004-6837-5009"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055632925","display_name":"Avihu Dekel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avihu Dekel","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023268703","display_name":"Luis Lastras","orcid":"https://orcid.org/0009-0006-2792-220X","observed_orcids":["https://orcid.org/0009-0006-2792-220X"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Lastras","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80801977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6213","last_page":"6218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0012000000569969416,"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/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8029999732971191},{"id":"https://openalex.org/keywords/kv-cache-reuse","display_name":"KV cache reuse","score":0.9079999923706055},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.6359999775886536},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.6679999828338623},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.8600000143051147}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.503600001335144},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2955000102519989},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2827000021934509},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C107826830","wikidata":"https://www.wikidata.org/wiki/Q929380","display_name":"Environmental resource management","level":1,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2026-2441","doi":"https://doi.org/10.21437/interspeech.2026-2441","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-2441","pdf_url":"https://www.isca-archive.org/interspeech_2026/sunder26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2026-2441","doi":"https://doi.org/10.21437/interspeech.2026-2441","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2026-2441","pdf_url":"https://www.isca-archive.org/interspeech_2026/sunder26_interspeech.pdf","source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225199769.pdf","grobid_xml":"https://content.openalex.org/works/W7225199769.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4377121468","https://openalex.org/W4381827575","https://openalex.org/W4385822293","https://openalex.org/W4388718054","https://openalex.org/W4391835492","https://openalex.org/W4400717319","https://openalex.org/W4401306886","https://openalex.org/W4416255707","https://openalex.org/W4416550218","https://openalex.org/W7126278909"],"related_works":["https://openalex.org/W7155056370","https://openalex.org/W7165711032","https://openalex.org/W7155053337","https://openalex.org/W4385822501","https://openalex.org/W4296069287","https://openalex.org/W4402118935","https://openalex.org/W7225199017","https://openalex.org/W4385822444","https://openalex.org/W2746265435","https://openalex.org/W4385822753"],"abstract_inverted_index":{"Word-level":[0],"timestamps":[1,15,37,55],"are":[2],"essential":[3],"for":[4,33,95],"many":[5],"speech":[6,26,34,42,84],"applications.Existing":[7],"methods":[8,138],"either":[9],"degrade":[10],"transcription":[11,60],"quality":[12],"when":[13,150],"interleaving":[14],"or":[16],"require":[17],"separate":[18],"alignment":[19,114],"models":[20],"that":[21,69],"do":[22],"not":[23],"integrate":[24],"into":[25],"LLMs.We":[27],"propose":[28,90],"a":[29,40,112],"parameter":[30],"efficient":[31],"framework":[32],"recognition":[35],"with":[36,54],"(SRWT)":[38],"within":[39],"single":[41],"LLM.Our":[43],"approach":[44],"generates":[45],"transcriptions":[46],"in":[47,56,116,127],"the":[48,57,122,135],"first":[49],"step":[50],"and":[51,125],"regenerates":[52],"them":[53],"second,":[58],"preserving":[59,109],"quality.We":[61],"introduce":[62],"modular":[63],"low":[64],"rank":[65],"adaptation":[66,82],"(LoRA)":[67],"variants":[68],"train":[70],"only":[71,152],"on":[72,147,153],"SRWT":[73],"data":[74,149],"without":[75],"degrading":[76],"base":[77,105,136],"model":[78,106],"capabilities,":[79],"enabling":[80,97],"isolated":[81],"as":[83],"LLMs":[85],"scale":[86],"to":[87,134],"more":[88],"tasks.We":[89],"novel":[91],"activated":[92],"LoRA":[93],"(aLoRA)":[94],"SRWT,":[96],"KV-cache":[98],"reuse":[99],"thus":[100],"allowing":[101],"improved":[102],"performance":[103],"through":[104],"usage":[107],"while":[108,130],"modularity.Experiments":[110],"show":[111],"27ms":[113],"error":[115,146],"English":[117],"(35%":[118],"relative":[119],"improvement":[120],"over":[121],"best":[123],"baseline)":[124],"21ms":[126],"multilingual":[128,148],"data,":[129],"maintaining":[131],"WER":[132],"identical":[133],"model.Proposed":[137],"also":[139],"exhibit":[140],"strong":[141],"zero-shot":[142],"transfer,":[143],"achieving":[144],"37ms":[145],"trained":[151],"English.":[154]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-04T00:00:00"}