{"id":"https://openalex.org/W4408352608","doi":"https://doi.org/10.1109/icassp49660.2025.10888128","title":"MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders","display_name":"MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352608","doi":"https://doi.org/10.1109/icassp49660.2025.10888128"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100991440","display_name":"Wenyu Zhang","orcid":"https://orcid.org/0000-0002-9706-8081"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102696734","display_name":"Shuo Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"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/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113268590","display_name":"Xunlong Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104978423","display_name":"Zhuohan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":"Zhuohan Liu","raw_affiliation_strings":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018641343","display_name":"Yunlei He","orcid":"https://orcid.org/0000-0003-2929-5554"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":"Yingxu He","raw_affiliation_strings":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101339717","display_name":"Geyu Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":"Geyu Lin","raw_affiliation_strings":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109309570","display_name":"Ai Ti Aw","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":["Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research (A*STAR),Institute for Infocomm Research (I2R), Agency for Science,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.128,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85121002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9926000237464905,"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/computer-science","display_name":"Computer science","score":0.6997509598731995},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6358234882354736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5373327732086182},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0738670825958252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997509598731995},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6358234882354736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5373327732086182},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0738670825958252}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2936774411","https://openalex.org/W2962854302","https://openalex.org/W2963686995","https://openalex.org/W3168867926","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4311000453","https://openalex.org/W4312048190","https://openalex.org/W4313014461","https://openalex.org/W4376312115","https://openalex.org/W4377372369","https://openalex.org/W4378501656","https://openalex.org/W4381827575","https://openalex.org/W4384918448","https://openalex.org/W4386351448","https://openalex.org/W4387891768","https://openalex.org/W4387994989","https://openalex.org/W4388718054","https://openalex.org/W4391021627","https://openalex.org/W4391591726","https://openalex.org/W4393903963","https://openalex.org/W4395022840","https://openalex.org/W4395474395","https://openalex.org/W4396945500","https://openalex.org/W4400104114","https://openalex.org/W4404784428","https://openalex.org/W4406033011"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancements":[2],"in":[3],"large":[4],"language":[5,12],"models":[6],"(LLMs)":[7],"have":[8],"significantly":[9,106],"enhanced":[10],"natural":[11],"processing":[13],"capabilities,":[14],"facilitating":[15],"the":[16,51,79,98,121],"development":[17],"of":[18,74,90,123],"AudioLLMs":[19,31,124],"that":[20,114],"process":[21],"and":[22,25,64],"understand":[23],"speech":[24],"audio":[26,36,48,53,99,128],"inputs":[27],"alongside":[28],"text.":[29],"Existing":[30],"typically":[32],"combine":[33],"a":[34,39,84,88],"pre-trained":[35,40,52],"encoder":[37,54,86],"with":[38,87],"LLM,":[41],"which":[42],"are":[43],"subsequently":[44],"finetuned":[45],"on":[46,97],"specific":[47],"tasks.":[49,129],"However,":[50],"has":[55],"constrained":[56],"capacity":[57],"to":[58,71,101,125],"capture":[59],"features":[60],"for":[61],"new":[62],"tasks":[63],"datasets.":[65],"To":[66],"address":[67],"this,":[68],"we":[69],"propose":[70],"incorporate":[72],"mixtures":[73],"\u2018weak\u2019":[75],"encoders":[76],"(MoWE)":[77],"into":[78],"AudioLLM":[80],"framework.":[81],"MoWE":[82,115],"supplements":[83],"base":[85],"pool":[89],"relatively":[91],"lightweight":[92],"encoders,":[93],"selectively":[94],"activated":[95],"based":[96],"input":[100],"enhance":[102],"feature":[103],"extraction":[104],"without":[105],"increasing":[107],"model":[108],"size.":[109],"Our":[110],"empirical":[111],"results":[112],"demonstrate":[113],"effectively":[116],"improves":[117],"multi-task":[118],"performance,":[119],"broadening":[120],"applicability":[122],"more":[126],"diverse":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}