{"id":"https://openalex.org/W4391021748","doi":"https://doi.org/10.1109/asru57964.2023.10389735","title":"Joint Prediction and Denoising for Large-Scale Multilingual Self-Supervised Learning","display_name":"Joint Prediction and Denoising for Large-Scale Multilingual Self-Supervised Learning","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021748","doi":"https://doi.org/10.1109/asru57964.2023.10389735"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5101779022","display_name":"William Chen","orcid":"https://orcid.org/0000-0002-3251-3084"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Chen","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101063912","display_name":"Jiatong Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125256","display_name":"Brian Yan","orcid":"https://orcid.org/0000-0002-4160-6282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024324721","display_name":"Dan Berrebbi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Berrebbi","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101779022"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79827692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8500304222106934},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6372151374816895},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5375627279281616},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5221524238586426},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5212717056274414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5014936923980713},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48037251830101013},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.447465717792511},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32338282465934753},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11324894428253174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500304222106934},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6372151374816895},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5375627279281616},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5221524238586426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5212717056274414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5014936923980713},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48037251830101013},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.447465717792511},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32338282465934753},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11324894428253174},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":57,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2973049979","https://openalex.org/W3095410713","https://openalex.org/W3097906045","https://openalex.org/W3119308075","https://openalex.org/W3129831491","https://openalex.org/W3134202725","https://openalex.org/W3197580070","https://openalex.org/W3197813307","https://openalex.org/W3198429080","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4224308101","https://openalex.org/W4224934179","https://openalex.org/W4226033575","https://openalex.org/W4281492411","https://openalex.org/W4281690148","https://openalex.org/W4285225959","https://openalex.org/W4286359908","https://openalex.org/W4287854499","https://openalex.org/W4311000453","https://openalex.org/W4311642023","https://openalex.org/W4319862255","https://openalex.org/W4319862635","https://openalex.org/W4323066695","https://openalex.org/W4372259817","https://openalex.org/W4378105483","https://openalex.org/W4379467083","https://openalex.org/W4385807461","https://openalex.org/W4385822397","https://openalex.org/W4385822439","https://openalex.org/W4385822617","https://openalex.org/W4385822952","https://openalex.org/W4385823192","https://openalex.org/W4385823338","https://openalex.org/W6631190155","https://openalex.org/W6696449567","https://openalex.org/W6739901393","https://openalex.org/W6771467084","https://openalex.org/W6778883912","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6810081322","https://openalex.org/W6810673746","https://openalex.org/W6838276489","https://openalex.org/W6838322825","https://openalex.org/W6839193947","https://openalex.org/W6847118041","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395","https://openalex.org/W6853400807"],"related_works":["https://openalex.org/W2748574964","https://openalex.org/W1996130883","https://openalex.org/W2888483922","https://openalex.org/W2367747139","https://openalex.org/W2566187525","https://openalex.org/W2367150592","https://openalex.org/W2378889330","https://openalex.org/W4243585476","https://openalex.org/W2375788348","https://openalex.org/W2387796150"],"abstract_inverted_index":{"Multilingual":[0],"self-supervised":[1],"learning":[2],"(SSL)":[3],"has":[4],"often":[5],"lagged":[6],"behind":[7],"state-of-the-art":[8],"(SOTA)":[9],"methods":[10],"due":[11,37],"to":[12,18,33,38,51,57,71,90,102],"the":[13,25,92,112,148],"expenses":[14],"and":[15,69,152,159],"complexity":[16],"required":[17],"handle":[19],"many":[20],"languages.":[21,78],"This":[22],"further":[23,124],"harms":[24],"reproducibility":[26],"of":[27,74,95,111,140,147],"SSL,":[28],"which":[29,64,135],"is":[30],"already":[31],"limited":[32,153],"few":[34],"research":[35,59],"groups":[36],"its":[39],"resource":[40],"usage.":[41],"We":[42,61,121,155],"show":[43,122],"that":[44,123],"more":[45,52,58],"powerful":[46],"techniques":[47],"can":[48,126,136],"actually":[49],"lead":[50],"efficient":[53],"pre-training,":[54],"opening":[55],"SSL":[56,116],"groups.":[60],"propose":[62],"WavLabLM,":[63,81],"extends":[65],"WavLM\u2019s":[66],"joint":[67],"prediction":[68],"denoising":[70],"40k":[72],"hours":[73],"data":[75],"across":[76],"136":[77],"To":[79],"build":[80],"we":[82],"devise":[83],"a":[84,130],"novel":[85],"multi-stage":[86],"pre-training":[87],"method,":[88],"designed":[89],"address":[91],"language":[93],"imbalance":[94],"multilingual":[96],"data.":[97],"WavLabLM":[98],"achieves":[99],"comparable":[100],"performance":[101,142],"XLS-R":[103],"on":[104],"ML-SUPERB":[105],"with":[106,118,129,143],"less":[107],"than":[108],"$10":[109],"\\%$":[110,139,146],"training":[113],"data,":[114,149],"making":[115],"realizable":[117],"academic":[119],"compute.":[120],"efficiency":[125],"be":[127],"achieved":[128],"vanilla":[131],"HuBERT":[132],"Base":[133],"model,":[134],"maintain":[137],"$94":[138],"XLS-R\u2019s":[141],"only":[144],"$3":[145],"4":[150],"GPUs,":[151],"trials.":[154],"open-source":[156],"all":[157],"code":[158],"models":[160],"in":[161],"ESPnet.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}