{"id":"https://openalex.org/W4221152838","doi":"https://doi.org/10.1109/icassp43922.2022.9747671","title":"Language Adaptive Cross-Lingual Speech Representation Learning with Sparse Sharing Sub-Networks","display_name":"Language Adaptive Cross-Lingual Speech Representation Learning with Sparse Sharing Sub-Networks","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221152838","doi":"https://doi.org/10.1109/icassp43922.2022.9747671"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747671","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5103070663","display_name":"Yizhou Lu","orcid":"https://orcid.org/0000-0003-1399-8079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yizhou Lu","raw_affiliation_strings":["ByteDance AI Lab,Speech & Audio Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,Speech & Audio Team","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041661723","display_name":"Mingkun Huang","orcid":"https://orcid.org/0000-0001-9501-1797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingkun Huang","raw_affiliation_strings":["ByteDance AI Lab,Speech & Audio Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,Speech & Audio Team","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048340011","display_name":"Xinghua Qu","orcid":"https://orcid.org/0000-0001-8072-2019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinghua Qu","raw_affiliation_strings":["ByteDance AI Lab,Speech & Audio Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,Speech & Audio Team","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506669","display_name":"Pengfei Wei","orcid":"https://orcid.org/0000-0001-8093-0803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Wei","raw_affiliation_strings":["ByteDance AI Lab,Speech & Audio Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,Speech & Audio Team","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance AI Lab,Speech & Audio Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,Speech & Audio Team","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4534,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8360986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6882","last_page":"6886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9927999973297119,"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/T11309","display_name":"Music and Audio Processing","score":0.9902999997138977,"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":0.8783448338508606},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6876304149627686},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6245558857917786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6154079437255859},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5264424085617065},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4780186414718628},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46552368998527527},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4512821137905121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42880794405937195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3211798667907715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8783448338508606},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6876304149627686},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6245558857917786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154079437255859},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5264424085617065},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4780186414718628},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46552368998527527},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4512821137905121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42880794405937195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3211798667907715},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747671","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2547875792","https://openalex.org/W2805003733","https://openalex.org/W2842511635","https://openalex.org/W2913340405","https://openalex.org/W2914120296","https://openalex.org/W2962824709","https://openalex.org/W2963266252","https://openalex.org/W2964309797","https://openalex.org/W2965862774","https://openalex.org/W2971840980","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W2998103904","https://openalex.org/W3003875258","https://openalex.org/W3015265920","https://openalex.org/W3016181583","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3096032230","https://openalex.org/W3096122506","https://openalex.org/W3116179216","https://openalex.org/W3167207712","https://openalex.org/W3173767661","https://openalex.org/W3174636484","https://openalex.org/W3175374354","https://openalex.org/W3197242296","https://openalex.org/W3197932033","https://openalex.org/W3198429080","https://openalex.org/W4210463634","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6751979845","https://openalex.org/W6767737316","https://openalex.org/W6771467084","https://openalex.org/W6775396121","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6787407267","https://openalex.org/W6788335241"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2997567050","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581"],"abstract_inverted_index":{"Unsupervised":[0],"cross-lingual":[1],"speech":[2,12,115],"representation":[3],"learning":[4],"(XLSR)":[5],"has":[6],"recently":[7],"shown":[8],"promising":[9],"results":[10,110],"in":[11],"recognition":[13,116],"by":[14,75],"leveraging":[15],"vast":[16],"amounts":[17],"of":[18,37],"unlabeled":[19],"data":[20],"across":[21],"multiple":[22],"languages.":[23,135],"However,":[24],"standard":[25],"XLSR":[26,51,126],"model":[27],"suffers":[28],"from":[29],"language":[30,38,47,59,72,88,94],"interference":[31],"problem":[32],"due":[33],"to":[34],"the":[35,101],"lack":[36],"specific":[39,73,89],"modeling":[40,74],"ability.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,55],"investigate":[46],"adaptive":[48,60],"training":[49],"on":[50,64,111,128],"models.":[52],"More":[53],"importantly,":[54],"propose":[56],"a":[57,97,112],"novel":[58],"pretraining":[61],"approach":[62],"based":[63],"sparse":[65,98],"sharing":[66],"sub-networks.":[67],"It":[68],"makes":[69],"room":[70],"for":[71,80],"pruning":[76],"out":[77],"unimportant":[78],"parameters":[79],"each":[81,93,107],"language,":[82],"without":[83],"requiring":[84],"any":[85],"manually":[86],"designed":[87],"component.":[90],"After":[91],"pruning,":[92],"only":[95],"maintains":[96],"sub-network,":[99],"while":[100],"sub-networks":[102],"are":[103],"partially":[104],"shared":[105],"with":[106],"other.":[108],"Experimental":[109],"downstream":[113],"multilingual":[114],"task":[117],"show":[118],"that":[119],"our":[120,137],"proposed":[121,138],"method":[122,139],"significantly":[123],"outperforms":[124,141],"baseline":[125],"models":[127],"both":[129],"high":[130],"resource":[131,134],"and":[132,145],"low":[133],"Besides,":[136],"consistently":[140],"other":[142],"adaptation":[143],"methods":[144],"requires":[146],"fewer":[147],"parameters.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}