{"id":"https://openalex.org/W4416036636","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.974","title":"Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders","display_name":"Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036636","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.974"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.974","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.974","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.974","pdf_url":"https://aclanthology.org/2025.emnlp-main.974.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.emnlp-main.974.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065538178","display_name":"Weiqiao Shan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqiao Shan","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032504077","display_name":"Yuang Li","orcid":"https://orcid.org/0000-0002-2244-0184","observed_orcids":["https://orcid.org/0000-0002-2244-0184","https://orcid.org/0009-0009-7480-7329"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuang Li","raw_affiliation_strings":["Huawei Translation Services Center , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center , Beijing , China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041171188","display_name":"Yuhao Zhang","orcid":"https://orcid.org/0009-0006-7268-2540","observed_orcids":["https://orcid.org/0009-0006-7268-2540"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen , China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057019417","display_name":"Yingfeng Luo","orcid":"https://orcid.org/0000-0003-1950-9045","observed_orcids":["https://orcid.org/0000-0003-1950-9045"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingfeng Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647360","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0003-0210","observed_orcids":["https://orcid.org/0000-0003-0003-0210","https://orcid.org/0009-0006-8422-5822"]},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Xu","raw_affiliation_strings":["College of Computer Science and Technology , Harbin Engineering University , Harbin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology , Harbin Engineering University , Harbin , China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025545388","display_name":"Xiaofeng Zhao","orcid":"https://orcid.org/0000-0003-0316-7220","observed_orcids":["https://orcid.org/0000-0003-0316-7220"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhao","raw_affiliation_strings":["Huawei Translation Services Center , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center , Beijing , China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038738242","display_name":"Long Meng","orcid":"https://orcid.org/0000-0001-8140-088X","observed_orcids":["https://orcid.org/0000-0001-8140-088X"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Meng","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113627163","display_name":"Yunfei Lu","orcid":"https://orcid.org/0000-0001-5363-6836","observed_orcids":["https://orcid.org/0000-0001-5363-6836"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Lu","raw_affiliation_strings":["Huawei Translation Services Center , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center , Beijing , China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402955","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-8343-372X","observed_orcids":["https://orcid.org/0000-0002-8343-372X"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Huawei Translation Services Center , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center , Beijing , China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005698391","display_name":"Hao Frank Yang","orcid":"https://orcid.org/0000-0001-8506-7295","observed_orcids":["https://orcid.org/0000-0001-8506-7295"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei Translation Services Center , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center , Beijing , China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600701","display_name":"Tong Xiao","orcid":"https://orcid.org/0000-0002-5842-6501","observed_orcids":["https://orcid.org/0000-0002-5842-6501"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["NiuTrans Research , Shenyang , China","School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NiuTrans Research , Shenyang , China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370145","display_name":"Jingbo Zhu","orcid":"https://orcid.org/0009-0006-6536-6822","observed_orcids":["https://orcid.org/0009-0006-6536-6822","https://orcid.org/0000-0001-9667-3071"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JingBo Zhu","raw_affiliation_strings":["NiuTrans Research , Shenyang , China","School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NiuTrans Research , Shenyang , China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9066,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87589949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"19316","last_page":"19331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.001500000013038516,"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":0.0007999999797903001,"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/speech-large-language-models","display_name":"speech large language models","score":0.9679999947547913},{"id":"https://openalex.org/keywords/audio-encoder","display_name":"audio encoder","score":0.746999979019165},{"id":"https://openalex.org/keywords/audio-representation-learning","display_name":"audio representation learning","score":0.328000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013000249862671},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5733000040054321},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4733999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C2776085556","wikidata":"https://www.wikidata.org/wiki/Q183361","display_name":"Chen","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.974","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.974","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.974","pdf_url":"https://aclanthology.org/2025.emnlp-main.974.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.974","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.974","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.974","pdf_url":"https://aclanthology.org/2025.emnlp-main.974.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6641886038","display_name":null,"funder_award_id":"B16009","funder_id":"https://openalex.org/F4320335785","funder_display_name":"Project 211"},{"id":"https://openalex.org/G7096855582","display_name":null,"funder_award_id":"U24A20334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G969350000","display_name":null,"funder_award_id":"B16009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335785","display_name":"Project 211","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036636.pdf","grobid_xml":"https://content.openalex.org/works/W4416036636.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411119438","https://openalex.org/W3205644108","https://openalex.org/W4415433985","https://openalex.org/W4411119642","https://openalex.org/W4385571338","https://openalex.org/W4404781855","https://openalex.org/W4416034044","https://openalex.org/W4415273318","https://openalex.org/W4385571513","https://openalex.org/W7140098989"],"abstract_inverted_index":{"Weiqiao":[0],"Shan,":[1],"Yuang":[2],"Li,":[3],"Yuhao":[4],"Zhang,":[5,17],"Yingfeng":[6],"Luo,":[7],"Chen":[8],"Xu,":[9],"Xiaofeng":[10],"Zhao,":[11],"Long":[12],"Meng,":[13],"Yunfei":[14],"Lu,":[15],"Min":[16],"Hao":[18],"Yang,":[19],"Tong":[20],"Xiao,":[21],"JingBo":[22],"Zhu.":[23],"Proceedings":[24],"of":[25],"the":[26],"2025":[27],"Conference":[28],"on":[29],"Empirical":[30],"Methods":[31],"in":[32],"Natural":[33],"Language":[34],"Processing.":[35],"2025.":[36]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-08T00:00:00"}
