{"id":"https://openalex.org/W4206662530","doi":"https://doi.org/10.1109/taslp.2022.3140552","title":"Optimizing Data Usage for Low-Resource Speech Recognition","display_name":"Optimizing Data Usage for Low-Resource Speech Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4206662530","doi":"https://doi.org/10.1109/taslp.2022.3140552"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3140552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3140552","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["X-LANCE, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"X-LANCE, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102974956","display_name":"Zhikai Zhou","orcid":"https://orcid.org/0000-0002-4626-2677"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Zhikai Zhou","raw_affiliation_strings":["X-LANCE, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4626-2677","affiliations":[{"raw_affiliation_string":"X-LANCE, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.9682,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87793762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"394","last_page":"403"},"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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.8194828629493713},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7480285167694092},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5472745895385742},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5161851048469543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4526684880256653},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4391135275363922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194828629493713},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7480285167694092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5472745895385742},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5161851048469543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4526684880256653},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4391135275363922}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3140552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3140552","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G1899722019","display_name":"\u6df1\u5ea6\u5b66\u4e60\u8bed\u97f3\u8bc6\u522b\u4e2d\u7684\u5feb\u901f\u9ad8\u6548\u81ea\u9002\u5e94\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3537961753","display_name":null,"funder_award_id":"62122050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W139772320","https://openalex.org/W1494198834","https://openalex.org/W1994126409","https://openalex.org/W2038909419","https://openalex.org/W2127982613","https://openalex.org/W2184170932","https://openalex.org/W2296073425","https://openalex.org/W2395387595","https://openalex.org/W2399153411","https://openalex.org/W2406677277","https://openalex.org/W2407080277","https://openalex.org/W2514191708","https://openalex.org/W2526425061","https://openalex.org/W2627092829","https://openalex.org/W2739883972","https://openalex.org/W2769437540","https://openalex.org/W2808640845","https://openalex.org/W2890964092","https://openalex.org/W2891816510","https://openalex.org/W2894835365","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963979492","https://openalex.org/W2964002616","https://openalex.org/W2964309797","https://openalex.org/W2971840980","https://openalex.org/W2972557594","https://openalex.org/W2982223350","https://openalex.org/W3007928779","https://openalex.org/W3015585292","https://openalex.org/W3015889230","https://openalex.org/W3026041220","https://openalex.org/W3035390927","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3081416955","https://openalex.org/W3093579165","https://openalex.org/W3095842703","https://openalex.org/W3096338464","https://openalex.org/W3096485810","https://openalex.org/W3115362515","https://openalex.org/W3160525311","https://openalex.org/W3196824004","https://openalex.org/W4286685063","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6687566353","https://openalex.org/W6739901393","https://openalex.org/W6746041127","https://openalex.org/W6752630080","https://openalex.org/W6759455113","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6784614252"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,44,47],"recognition":[2,48],"has":[3],"made":[4],"huge":[5],"progress":[6],"recently.":[7],"However,":[8],"the":[9,21,39,72,75,92,99,125,137,150,153,163,184,220],"current":[10],"modeling":[11],"strategy":[12,127],"still":[13],"suffers":[14],"a":[15,33,50,80,169],"large":[16],"performance":[17],"degradation":[18],"when":[19],"facing":[20],"low-resource":[22,43,53,133,222],"languages":[23,60,143,181],"with":[24,156,183,204],"limited":[25,157],"training":[26,88],"data.":[27,158],"In":[28],"this":[29],"paper,":[30],"we":[31],"propose":[32],"series":[34],"of":[35,74],"methods":[36,123],"to":[37,83,171],"optimize":[38],"data":[40,85,109,115,130,165],"usage":[41,131,166],"for":[42,64,108,114,132,144,178,219],"recognition.":[45],"Multilingual":[46],"helps":[49],"lot":[51],"in":[52,67,94],"scenarios.":[54],"The":[55,193],"correlation":[56],"and":[57,111,147,196,208],"similarity":[58],"between":[59],"are":[61,117,198],"further":[62],"exploited":[63],"multilingual":[65,187],"pretraining":[66,145],"our":[68],"work.":[69],"We":[70,135],"utilize":[71],"posterior":[73],"target":[76,100,154,180,221],"language":[77,81,101,155],"extracted":[78],"from":[79],"classifier":[82],"perform":[84],"weighing":[86],"on":[87,128,152,190,201],"samples,":[89],"which":[90],"assists":[91],"model":[93,151],"being":[95],"more":[96],"biased":[97],"towards":[98],"during":[102],"pretraining.":[103],"Furthermore,":[104],"dynamic":[105],"curriculum":[106],"learning":[107],"allocation":[110],"length":[112],"perturbation":[113],"augmentation":[116],"also":[118,199],"designed.":[119],"All":[120],"these":[121],"three":[122],"form":[124],"new":[126],"optimized":[129],"languages.":[134],"evaluate":[136],"proposed":[138,164],"method":[139,167,189],"using":[140],"rich":[141],"resource":[142],"(PT)":[146],"finetuning":[148],"(FT)":[149],"Experimental":[159],"results":[160],"show":[161],"that":[162],"obtains":[168],"15":[170],"25&#x0025;":[172],"relative":[173,211],"word":[174],"error":[175,213],"rate":[176,214],"reduction":[177,215],"different":[179],"compared":[182],"commonly":[185],"adopted":[186],"PT+FT":[188],"CommonVoice":[191],"dataset.":[192],"same":[194],"improvement":[195],"conclusion":[197],"observed":[200],"Babel":[202],"dataset":[203],"conversational":[205],"telephone":[206],"speech,":[207],"<inline-formula><tex-math":[209],"notation=\"LaTeX\">$\\sim$</tex-math></inline-formula>40&#x0025;":[210],"character":[212],"can":[216],"be":[217],"obtained":[218],"language.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}