{"id":"https://openalex.org/W4392904753","doi":"https://doi.org/10.1109/icassp48485.2024.10446335","title":"Stable Distillation: Regularizing Continued Pre-Training for Low-Resource Automatic Speech Recognition","display_name":"Stable Distillation: Regularizing Continued Pre-Training for Low-Resource Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904753","doi":"https://doi.org/10.1109/icassp48485.2024.10446335"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446335","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5018932560","display_name":"Ashish Seth","orcid":"https://orcid.org/0000-0003-3100-9342"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ashish Seth","raw_affiliation_strings":["IIT,Madras,India","IIT, Madras, India"],"affiliations":[{"raw_affiliation_string":"IIT,Madras,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"IIT, Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033408639","display_name":"Sreyan Ghosh","orcid":"https://orcid.org/0000-0003-3773-561X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["IIT,Madras,India","IIT, Madras, India"],"affiliations":[{"raw_affiliation_string":"IIT,Madras,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"IIT, Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018932560"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02632844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10821","last_page":"10825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9977999925613403,"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/distillation","display_name":"Distillation","score":0.8521270155906677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7667797207832336},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7028487920761108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6123850345611572},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5617344379425049},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5373505353927612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.526267409324646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4991767406463623},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4588746130466461},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4457029402256012},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.43803149461746216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43060487508773804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3767901659011841},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11990970373153687},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.07304263114929199}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.8521270155906677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667797207832336},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7028487920761108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6123850345611572},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5617344379425049},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5373505353927612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.526267409324646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4991767406463623},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4588746130466461},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4457029402256012},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43803149461746216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43060487508773804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3767901659011841},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11990970373153687},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.07304263114929199},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446335","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2111296615","https://openalex.org/W2166637769","https://openalex.org/W2766219058","https://openalex.org/W2895103375","https://openalex.org/W2906967080","https://openalex.org/W2982223350","https://openalex.org/W3006051380","https://openalex.org/W3008008574","https://openalex.org/W3034238904","https://openalex.org/W3035390927","https://openalex.org/W3036601975","https://openalex.org/W3104215796","https://openalex.org/W3176693010","https://openalex.org/W3197580070","https://openalex.org/W3198771897","https://openalex.org/W3203098807","https://openalex.org/W3209059054","https://openalex.org/W4283073456","https://openalex.org/W4287075881","https://openalex.org/W4287692509","https://openalex.org/W4297841896","https://openalex.org/W4313195213","https://openalex.org/W4319862633","https://openalex.org/W6758531748","https://openalex.org/W6774085601","https://openalex.org/W6780218876","https://openalex.org/W6781421678","https://openalex.org/W6798423582","https://openalex.org/W6849406959"],"related_works":["https://openalex.org/W3144173820","https://openalex.org/W2130553454","https://openalex.org/W2237505347","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W3104108945","https://openalex.org/W3163689946","https://openalex.org/W4287890939"],"abstract_inverted_index":{"Continued":[0],"self-supervised":[1],"(SSL)":[2],"pre-training":[3,38,72,87,119],"for":[4,19,35,61,141],"adapting":[5],"existing":[6],"SSL":[7,91],"models":[8],"to":[9,15,116,125,128],"the":[10,44,65,75,95,103,108,131,146],"target":[11,45,78,96,147],"domain":[12,46,97],"has":[13],"shown":[14],"be":[16,126],"extremely":[17],"effective":[18],"low-resource":[20],"Automatic":[21],"Speech":[22],"Recognition":[23],"(ASR).":[24],"This":[25,136],"paper":[26],"proposes":[27],"Stable":[28,55,151],"Distillation,":[29],"a":[30,68,114],"simple":[31],"and":[32,50,77,100],"novel":[33],"approach":[34],"SSL-based":[36],"continued":[37,62,71,86,118],"that":[39,129],"boosts":[40],"ASR":[41,98,143],"performance":[42],"in":[43,164],"where":[47],"both":[48],"labeled":[49],"unlabeled":[51],"data":[52],"are":[53],"limited.":[54],"Distillation":[56,152],"employs":[57],"self-distillation":[58],"as":[59,113],"regularization":[60],"pre-training,":[63],"alleviating":[64],"over-fitting":[66],"issue,":[67],"common":[69],"problem":[70],"faces":[73],"when":[74,162],"source":[76],"domains":[79],"differ.":[80],"Specifically,":[81],"first,":[82],"we":[83,106],"perform":[84,117],"vanilla":[85],"on":[88,94,145],"an":[89],"initial":[90,110],"pre-trained":[92,111],"model":[93,112],"dataset":[99],"call":[101],"it":[102],"teacher.":[104],"Next,":[105],"take":[107],"same":[109],"student":[115,137],"while":[120],"enforcing":[121],"its":[122],"hidden":[123],"representations":[124],"close":[127],"of":[130],"teacher":[132],"(via":[133],"MSE":[134],"loss).":[135],"is":[138],"then":[139],"used":[140],"downstream":[142],"fine-tuning":[144],"dataset.":[148],"In":[149],"practice,":[150],"outperforms":[153],"all":[154],"our":[155],"baselines":[156],"by":[157],"0.8":[158],"-":[159],"7":[160],"WER":[161],"evaluated":[163],"various":[165],"experimental":[166],"settings<sup":[167],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[169]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}