{"id":"https://openalex.org/W7105669668","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228863","title":"Incremental Tucker Decomposition for Scalable and Efficient Multilingual Speech Recognition","display_name":"Incremental Tucker Decomposition for Scalable and Efficient Multilingual Speech Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105669668","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228863"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Guanghui Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanghui Song","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ye Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Hong","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xitong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xitong Gao","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Juanjuan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanjuan Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kejiang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejiang Ye","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79505012,"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":0.9613000154495239,"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":0.9613000154495239,"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":0.0210999995470047,"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/T10863","display_name":"Voice and Speech Disorders","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7986000180244446},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6331999897956848},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5027999877929688},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4672999978065491},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4343000054359436},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4133000075817108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521999716758728},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7986000180244446},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5468000173568726},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4494999945163727},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2024165284","https://openalex.org/W2078841894","https://openalex.org/W2750545698","https://openalex.org/W2759071281","https://openalex.org/W3015208154","https://openalex.org/W3037399553","https://openalex.org/W3097106378","https://openalex.org/W3198455051","https://openalex.org/W4402112032","https://openalex.org/W4402671180"],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"face":[6],"challenges":[7],"in":[8,112],"efficiently":[9],"integrating":[10],"new":[11,55],"languages":[12,56],"while":[13,86],"maintaining":[14],"scalability":[15],"and":[16,42,101,115],"performance.":[17],"This":[18,96],"paper":[19],"introduces":[20],"an":[21,44],"Incremental":[22],"Tucker-based":[23],"Low-Rank":[24],"Adaptation":[25],"(LoRA)":[26],"framework":[27,50,97],"designed":[28],"to":[29,37,79,82,117],"address":[30],"these":[31],"limitations.":[32],"By":[33],"leveraging":[34],"Tucker":[35],"decomposition":[36],"compress":[38],"multilingual":[39,106],"LoRA":[40],"parameters":[41],"introducing":[43],"efficient":[45],"incremental":[46],"learning":[47],"mechanism,":[48],"the":[49,59,64,71],"enables":[51],"seamless":[52],"addition":[53],"of":[54],"without":[57],"re-computing":[58],"full":[60],"decomposition.":[61],"Experiments":[62],"on":[63],"Mozilla":[65],"Common":[66],"Voice":[67],"dataset":[68],"demonstrate":[69],"that":[70],"proposed":[72],"approach":[73],"reduces":[74],"parameter":[75],"requirements":[76],"by":[77],"up":[78],"80%":[80],"compared":[81],"traditional":[83],"LoRA-based":[84],"methods,":[85],"achieving":[87],"competitive":[88],"Word":[89],"Error":[90],"Rates":[91],"(WER)":[92],"across":[93],"diverse":[94],"languages.":[95],"provides":[98],"a":[99],"scalable":[100],"resource-efficient":[102],"solution":[103],"for":[104],"modern":[105],"ASR":[107],"systems,":[108],"offering":[109],"significant":[110],"advantages":[111],"memory":[113],"efficiency":[114],"adaptability":[116],"dynamic":[118],"language":[119],"expansion.":[120]},"counts_by_year":[],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-11-14T00:00:00"}