{"id":"https://openalex.org/W7148479973","doi":"https://doi.org/10.1109/asru65441.2025.11434637","title":"Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models","display_name":"Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148479973","doi":"https://doi.org/10.1109/asru65441.2025.11434637"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434637","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/A5101991100","display_name":"Qiongqiong Wang","orcid":"https://orcid.org/0000-0002-9903-0618"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Qiongqiong Wang","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129705776","display_name":"Jeremy H. M. Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jeremy H. M. Wong","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013047791","display_name":"Tianchi Liu","orcid":"https://orcid.org/0000-0003-3472-0703"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianchi Liu","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132808088","display_name":"Shuo Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuo Sun","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132805172","display_name":"Wenyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenyu Zhang","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112588637","display_name":"Muhammad Huzaifah","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Muhammad Huzaifah","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130153207","display_name":"Nancy F. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy Chen","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109309570","display_name":"Ai Ti Aw","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ai Ti Aw","raw_affiliation_strings":["Institute of Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101991100"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87358758,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3553999960422516,"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/T10028","display_name":"Topic Modeling","score":0.3553999960422516,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.18359999358654022,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11500000208616257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/paralanguage","display_name":"Paralanguage","score":0.9945999979972839},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6227999925613403},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.39469999074935913},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.3215999901294708},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.29249998927116394}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9945999979972839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355000138282776},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5738999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42559999227523804},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27649998664855957},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2780130068","wikidata":"https://www.wikidata.org/wiki/Q2208651","display_name":"Transversal (combinatorics)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434637","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":[{"display_name":"Quality Education","score":0.7251806855201721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2146334809","https://openalex.org/W2726515241","https://openalex.org/W2970641574","https://openalex.org/W2973072704","https://openalex.org/W3209984917","https://openalex.org/W4361994820","https://openalex.org/W4385822293","https://openalex.org/W4391021627","https://openalex.org/W4392902623","https://openalex.org/W4392903888","https://openalex.org/W4393147046","https://openalex.org/W4402112110","https://openalex.org/W4402669711","https://openalex.org/W4402683976","https://openalex.org/W4402684170","https://openalex.org/W4404782655","https://openalex.org/W4406859696","https://openalex.org/W4408354168","https://openalex.org/W4411112886","https://openalex.org/W4411119642","https://openalex.org/W4412945306","https://openalex.org/W4415433576","https://openalex.org/W4415433622"],"related_works":[],"abstract_inverted_index":{"Current":[0],"large":[1],"speech":[2,79],"language":[3],"models":[4],"(SpeechLLMs)":[5],"often":[6],"exhibit":[7],"limitations":[8],"in":[9,104],"empathetic":[10],"reasoning,":[11],"primarily":[12],"due":[13],"to":[14,35,55],"the":[15,56,99,111],"absence":[16],"of":[17],"training":[18,67],"datasets":[19],"that":[20,47,63],"integrate":[21],"both":[22,72],"contextual":[23,37,105],"content":[24],"and":[25,58,74],"paralinguistic":[26,38,49,106],"cues.":[27],"In":[28],"this":[29],"work,":[30],"we":[31],"propose":[32],"two":[33],"approaches":[34],"incorporate":[36],"information":[39],"into":[40],"model":[41],"training:":[42],"(1)":[43],"an":[44,60],"explicit":[45,100],"method":[46,62,83],"provides":[48],"metadata":[50],"(e.g.,":[51],"emotion":[52,76],"annotations)":[53],"directly":[54],"LLM,":[57],"(2)":[59],"implicit":[61,82],"automatically":[64],"generates":[65],"novel":[66],"question-answer":[68],"(QA)":[69],"pairs":[70],"using":[71],"categorical":[73],"dimensional":[75],"annotations":[77],"alongside":[78],"transcriptions.":[80],"Our":[81],"boosts":[84],"performance":[85],"(LLM-judged)":[86],"by":[87,114],"38.41%":[88],"on":[89],"a":[90],"human-annotated":[91],"QA":[92],"benchmark,":[93],"reaching":[94],"46.02%":[95],"when":[96],"combined":[97],"with":[98,118],"approach,":[101],"showing":[102],"effectiveness":[103],"understanding.":[107],"We":[108],"also":[109],"validate":[110],"LLM":[112],"judge":[113],"demonstrating":[115],"its":[116,124],"correlation":[117],"classification":[119],"metrics,":[120],"providing":[121],"support":[122],"for":[123],"reliability.":[125]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}