{"id":"https://openalex.org/W4372348492","doi":"https://doi.org/10.1109/icassp49357.2023.10094300","title":"Learning ASR Pathways: A Sparse Multilingual ASR Model","display_name":"Learning ASR Pathways: A Sparse Multilingual ASR Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348492","doi":"https://doi.org/10.1109/icassp49357.2023.10094300"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5040945367","display_name":"Mu Yang","orcid":"https://orcid.org/0009-0009-0883-1910"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mu Yang","raw_affiliation_strings":["University of Texas at Dallas,Center for Robust Speech Systems (CRSS),USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Center for Robust Speech Systems (CRSS),USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069296252","display_name":"Chunxi Liu","orcid":"https://orcid.org/0000-0001-5441-9374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunxi Liu","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325058","display_name":"David Zhang","orcid":"https://orcid.org/0000-0002-5027-5286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Zhang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103098852","display_name":"Duc Le","orcid":"https://orcid.org/0000-0001-9490-2563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040945367"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.5347,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85791991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.8767235279083252},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7518693804740906},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.731338381767273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6234207153320312},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5914934873580933},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4451856017112732},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.380764365196228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8767235279083252},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7518693804740906},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.731338381767273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6234207153320312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5914934873580933},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4451856017112732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.380764365196228},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2764043458","https://openalex.org/W2767785892","https://openalex.org/W2805003733","https://openalex.org/W2910715461","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2963376890","https://openalex.org/W2964309797","https://openalex.org/W2971840980","https://openalex.org/W2975044525","https://openalex.org/W2998103904","https://openalex.org/W3015194534","https://openalex.org/W3095410713","https://openalex.org/W3096032230","https://openalex.org/W3097338456","https://openalex.org/W3097777922","https://openalex.org/W3104263050","https://openalex.org/W3144557079","https://openalex.org/W3156323585","https://openalex.org/W3162309234","https://openalex.org/W3162649911","https://openalex.org/W3162665866","https://openalex.org/W3198429080","https://openalex.org/W3207326706","https://openalex.org/W3207629995","https://openalex.org/W3212799896","https://openalex.org/W3213029956","https://openalex.org/W4210463634","https://openalex.org/W4221138270","https://openalex.org/W4221143481","https://openalex.org/W4221152838","https://openalex.org/W4281770669","https://openalex.org/W6751979845","https://openalex.org/W6780482815"],"related_works":["https://openalex.org/W3047144510","https://openalex.org/W1989705153","https://openalex.org/W2386387936","https://openalex.org/W2789919619","https://openalex.org/W2326122716","https://openalex.org/W2496228846","https://openalex.org/W2293457016","https://openalex.org/W142374489","https://openalex.org/W2359001871","https://openalex.org/W1919409675"],"abstract_inverted_index":{"Neural":[0],"network":[1],"pruning":[2,15,27],"compresses":[3],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"models":[8,114],"effectively.":[9],"However,":[10],"in":[11],"multilingual":[12,48,83],"ASR,":[13],"language-agnostic":[14,26],"may":[16,29],"lead":[17],"to":[18,90,128],"severe":[19],"performance":[20,123],"drops":[21],"on":[22,99,124],"some":[23],"languages":[24,33,80,101,126],"because":[25],"masks":[28],"not":[30],"fit":[31],"all":[32],"and":[34,94,115,120],"discard":[35],"important":[36],"language-specific":[37,53],"parameters.":[38],"In":[39],"this":[40],"work,":[41],"we":[42],"present":[43],"ASR":[44,49,92,109],"pathways,":[45,93],"a":[46,87,103,116],"sparse":[47,131],"model":[50],"that":[51,57],"activates":[52],"sub-networks":[54],"(\"pathways\"),":[55],"such":[56],"the":[58,67,70,96,129],"parameters":[59,72],"for":[60,78],"each":[61],"language":[62],"are":[63],"learned":[64],"explicitly.":[65],"With":[66],"overlapping":[68],"sub-networks,":[69],"shared":[71],"can":[73],"also":[74],"enable":[75],"knowledge":[76],"transfer":[77],"lower-resource":[79],"via":[81],"joint":[82],"training.":[84],"We":[85],"propose":[86],"novel":[88],"algorithm":[89],"learn":[91],"evaluate":[95],"proposed":[97,108],"method":[98],"4":[100],"with":[102],"streaming":[104],"RNN-T":[105],"model.":[106],"Our":[107],"pathways":[110],"outperform":[111],"both":[112],"dense":[113],"language-agnostically":[117],"pruned":[118],"model,":[119],"provide":[121],"better":[122],"low-resource":[125],"compared":[127],"monolingual":[130],"models.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}