{"id":"https://openalex.org/W4388820319","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317133","title":"Progressive Multi-scale Self-supervised Learning for Speech Recognition","display_name":"Progressive Multi-scale Self-supervised Learning for Speech Recognition","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820319","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317133"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317133","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5011133553","display_name":"Genshun Wan","orcid":"https://orcid.org/0000-0002-5813-9430"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Genshun Wan","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442516","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0001-9999-1358"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686720","display_name":"Tan Liu","orcid":"https://orcid.org/0000-0003-4535-0963"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Liu","raw_affiliation_strings":["iFLYTEK Co. Ltd.,iFLYTEK Research,China","iFLYTEK Research, iFLYTEK Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK Co. Ltd.,iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106483978","display_name":"Chenxi Wang","orcid":"https://orcid.org/0009-0006-3334-2092"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Wang","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Co. Ltd.,iFLYTEK Research,China","iFLYTEK Research, iFLYTEK Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK Co. Ltd.,iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065761465","display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011133553"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15011449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"978","last_page":"982"},"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":0.9997000098228455,"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":0.9959999918937683,"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":0.8044911026954651},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6275230646133423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.60157710313797},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5975030660629272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5626299381256104},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5296406745910645},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5240861773490906},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.495702862739563},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4883129596710205},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4820062220096588},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.430670827627182},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38833123445510864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10414683818817139},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06972545385360718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044911026954651},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6275230646133423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.60157710313797},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5975030660629272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626299381256104},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5296406745910645},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5240861773490906},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.495702862739563},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4883129596710205},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4820062220096588},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.430670827627182},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38833123445510864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10414683818817139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06972545385360718},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317133","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2120615054","https://openalex.org/W2127141656","https://openalex.org/W2896457183","https://openalex.org/W2963735467","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W3015356564","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3096338464","https://openalex.org/W3139918052","https://openalex.org/W3197223534","https://openalex.org/W3209059054","https://openalex.org/W4224934179","https://openalex.org/W4385245566","https://openalex.org/W6687566353","https://openalex.org/W6725939724","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6784436999","https://openalex.org/W6791904447","https://openalex.org/W6810944559","https://openalex.org/W6947929050"],"related_works":["https://openalex.org/W1586607209","https://openalex.org/W122912556","https://openalex.org/W4312414840","https://openalex.org/W2621411691","https://openalex.org/W2271357838","https://openalex.org/W2556866732","https://openalex.org/W2328989934","https://openalex.org/W2348322200","https://openalex.org/W2981952041","https://openalex.org/W3148060700"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,39,44,60,81],"has":[2],"shown":[3],"great":[4],"potential":[5],"in":[6,16],"improving":[7],"automatic":[8],"speech":[9],"recognition":[10,17],"(ASR)":[11],"systems.":[12],"However,":[13],"further":[14],"improvements":[15],"performance":[18],"could":[19],"be":[20],"achieved":[21],"if":[22],"models":[23],"focus":[24],"on":[25,97,120,128],"audio":[26],"content":[27],"information":[28],"learning.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,83],"propose":[34],"a":[35,85,109],"progressive":[36,51],"multi-scale":[37,86],"self-supervised":[38,59],"method":[40,96,107],"that":[41],"reinforces":[42],"the":[43,63,77,80,89,98,121],"process":[45],"from":[46],"easy":[47],"to":[48,57,75],"difficult.":[49],"Our":[50,105],"strategy":[52],"utilizes":[53],"fine-grained":[54],"target":[55,69],"sets":[56,70],"compute":[58],"loss":[61],"at":[62,71],"top":[64],"layer":[65],"while":[66],"using":[67],"coarse-grained":[68],"intermediate":[72],"layers.":[73],"Additionally,":[74],"match":[76],"difficulty":[78],"of":[79,116],"process,":[82],"introduce":[84],"structure":[87],"into":[88],"multi-head":[90],"self-attention":[91],"module.":[92],"We":[93],"evaluate":[94],"our":[95],"Librispeech":[99],"dataset":[100],"and":[101,118,130],"demonstrate":[102],"its":[103],"effectiveness.":[104],"proposed":[106],"achieves":[108],"relative":[110],"word":[111],"error":[112],"rate":[113],"(WER)":[114],"reduction":[115],"13.7%":[117],"12.7%":[119],"test_other":[122],"evaluation":[123],"subsets,":[124,132],"respectively,":[125],"when":[126],"fine-tuned":[127],"10-hour":[129],"100-hour":[131],"outperforming":[133],"HuBERT.":[134]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}