{"id":"https://openalex.org/W4408353810","doi":"https://doi.org/10.1109/icassp49660.2025.10890091","title":"Optimizing Speech Multi-View Feature Fusion through Conditional Computation","display_name":"Optimizing Speech Multi-View Feature Fusion through Conditional Computation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353810","doi":"https://doi.org/10.1109/icassp49660.2025.10890091"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890091","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/A5065538178","display_name":"Weiqiao Shan","orcid":null},"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":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041171188","display_name":"Yuhao Zhang","orcid":"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/A5100383647","display_name":"Yuchen Han","orcid":"https://orcid.org/0000-0001-5610-9150"},"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":"Yuchen Han","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052270435","display_name":"Bei Li","orcid":"https://orcid.org/0000-0002-9121-6688"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Li","raw_affiliation_strings":["Meituan,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan,Beijing,China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025545388","display_name":"Xiaofeng Zhao","orcid":"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/A5032504077","display_name":"Yuang Li","orcid":"https://orcid.org/0000-0002-2244-0184"},"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/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"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 Yang","orcid":"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"},"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":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370155","display_name":"Jingbo Zhu","orcid":"https://orcid.org/0000-0002-6537-7007"},"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":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03920578,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9648000001907349,"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":0.9648000001907349,"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":0.7811933755874634},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5931847095489502},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5866012573242188},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5634839534759521},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5392225384712219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44740182161331177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3400527536869049},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18738842010498047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811933755874634},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5931847095489502},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5866012573242188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5634839534759521},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5392225384712219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44740182161331177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3400527536869049},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18738842010498047},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890091","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/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1613249581","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2809290718","https://openalex.org/W2963532001","https://openalex.org/W2973049979","https://openalex.org/W3087931390","https://openalex.org/W3148388528","https://openalex.org/W3175530672","https://openalex.org/W3176382501","https://openalex.org/W3209059054","https://openalex.org/W4205267278","https://openalex.org/W4225534571","https://openalex.org/W4385572506","https://openalex.org/W4389524500","https://openalex.org/W4389687998","https://openalex.org/W4392902920","https://openalex.org/W4402671987","https://openalex.org/W6723019446","https://openalex.org/W6739901393","https://openalex.org/W6769227307","https://openalex.org/W6771876938","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6810667325","https://openalex.org/W6853400807","https://openalex.org/W6854191273","https://openalex.org/W6857589352","https://openalex.org/W6866391187"],"related_works":["https://openalex.org/W4231775656","https://openalex.org/W2046435967","https://openalex.org/W2383646825","https://openalex.org/W2371018915","https://openalex.org/W2354191502","https://openalex.org/W1972225038","https://openalex.org/W3134658850","https://openalex.org/W2355938171","https://openalex.org/W2780079842","https://openalex.org/W3147584709"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"have":[2],"highlighted":[3],"the":[4,107],"efficacy":[5],"of":[6,43],"self-supervised":[7],"learning":[8],"(SSL)":[9],"features":[10,29,38],"in":[11,41,57],"various":[12],"speech-related":[13],"tasks,":[14],"providing":[15],"lightweight":[16],"and":[17,65,75,86,93],"versatile":[18],"multi-view":[19,80],"speech":[20,103],"representations.":[21],"However,":[22],"our":[23,89],"study":[24],"reveals":[25],"that":[26],"while":[27],"SSL":[28,85],"expedite":[30],"model":[31,77],"convergence,":[32],"they":[33],"conflict":[34],"with":[35,98],"traditional":[36],"spectral":[37,87,99],"like":[39],"FBanks":[40],"terms":[42],"update":[44],"directions.":[45],"In":[46],"response,":[47],"we":[48],"propose":[49],"a":[50,61,66],"novel":[51],"generalized":[52],"feature":[53,73],"fusion":[54],"framework":[55,71],"grounded":[56],"conditional":[58],"computation,":[59],"featuring":[60],"gradient-sensitive":[62],"gating":[63],"network":[64],"multi-stage":[67],"dropout":[68],"strategy.":[69],"This":[70],"mitigates":[72],"conflicts":[74],"bolsters":[76],"robustness":[78],"to":[79],"input":[81],"features.":[82],"By":[83],"integrating":[84],"features,":[88],"approach":[90],"accelerates":[91],"convergence":[92],"maintains":[94],"performance":[95],"on":[96,106],"par":[97],"models":[100],"across":[101],"multiple":[102],"translation":[104],"tasks":[105],"MUSTC":[108],"dataset.":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
