{"id":"https://openalex.org/W7148455755","doi":"https://doi.org/10.1109/asru65441.2025.11434599","title":"Diversity and complementarity of speech encoders across diverse tasks in a multi-modal large language model","display_name":"Diversity and complementarity of speech encoders across diverse tasks in a multi-modal large language model","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148455755","doi":"https://doi.org/10.1109/asru65441.2025.11434599"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434599","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/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":true,"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/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/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/A5102696734","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/A5047309615","display_name":"Kye Min Tan","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":"Kye Min Tan","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/A5015829772","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0001-9760-8343"},"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":"Bin 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/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":false,"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/A5100991440","display_name":"Wenyu Zhang","orcid":"https://orcid.org/0000-0002-9706-8081"},"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/A5113268590","display_name":"Xunlong Zou","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":"Xunlong Zou","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/A5132750728","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 F. 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":11,"corresponding_author_ids":["https://openalex.org/A5129705776"],"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":0.87354896,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.28790000081062317,"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":0.28790000081062317,"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/T12031","display_name":"Speech and dialogue systems","score":0.19850000739097595,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.12929999828338623,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.6783999800682068},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4724999964237213},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40400001406669617},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.361299991607666},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.2953000068664551}],"concepts":[{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.6783999800682068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6510000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47699999809265137},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434599","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7103947401046753,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2146334809","https://openalex.org/W2912904516","https://openalex.org/W2962834855","https://openalex.org/W2963242190","https://openalex.org/W2963686995","https://openalex.org/W2973072704","https://openalex.org/W2981087920","https://openalex.org/W2995181338","https://openalex.org/W3015591594","https://openalex.org/W3196509775","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3205644108","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4385571440","https://openalex.org/W4392902623","https://openalex.org/W4400033239","https://openalex.org/W4402112192","https://openalex.org/W4402669711","https://openalex.org/W4404781855","https://openalex.org/W4408352608","https://openalex.org/W4411119642","https://openalex.org/W4415188578"],"related_works":[],"abstract_inverted_index":{"A":[0],"Large":[1],"Language":[2],"Model":[3],"(LLM)":[4],"can":[5,43,59,145],"be":[6,44,60],"extended":[7],"to":[8,17,117,133],"understand":[9],"speech":[10,15,36,47,66,81],"inputs":[11],"by":[12,63],"using":[13,64],"a":[14,28,38,71,86],"encoder":[16],"compute":[18],"embeddings":[19],"from":[20],"the":[21,75,92],"speech,":[22],"which":[23],"are":[24],"then":[25],"used":[26,84],"with":[27],"text":[29],"prompt.":[30],"Diverse":[31],"information":[32,53],"is":[33,111,124],"expressed":[34],"in":[35,85,96],"and":[37,55,77,139],"wide":[39],"variety":[40],"of":[41,74,99],"tasks":[42,131],"performed.":[45],"Different":[46],"encoders":[48,93,110,123],"may":[49],"specialise":[50],"toward":[51],"different":[52],"types":[54],"tasks.":[56],"This":[57,68],"complementarity":[58,78,144],"leveraged":[61],"upon":[62],"multiple":[65],"encoders.":[67],"paper":[69],"presents":[70],"comprehensive":[72],"analysis":[73],"diversity":[76,108],"between":[79,109,122],"open-source":[80],"encoders,":[82],"when":[83],"multi-modal":[87],"LLM":[88],"framework.":[89],"Experiments":[90],"identify":[91],"that":[94,114,129,143],"excel":[95],"each":[97],"type":[98],"downstream":[100],"task,":[101],"thereby":[102],"guiding":[103],"future":[104],"system":[105],"design.":[106],"The":[107],"measured,":[112],"showing":[113,128],"Whisper":[115],"tends":[116],"behave":[118],"more":[119,135],"differently.":[120],"Diversity":[121],"compared":[125],"across":[126],"tasks,":[127],"semantic":[130],"tend":[132],"yield":[134,146],"diverse":[136],"predictions.":[137],"Early":[138],"late":[140],"fusion":[141],"show":[142],"improvements.":[147]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}