{"id":"https://openalex.org/W4310113560","doi":"https://doi.org/10.1145/3568562.3568645","title":"Improving Self-supervised Audio Representation based on Contrastive Learning with Conformer Encoder","display_name":"Improving Self-supervised Audio Representation based on Contrastive Learning with Conformer Encoder","publication_year":2022,"publication_date":"2022-11-29","ids":{"openalex":"https://openalex.org/W4310113560","doi":"https://doi.org/10.1145/3568562.3568645"},"language":"en","primary_location":{"id":"doi:10.1145/3568562.3568645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568562.3568645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 11th International Symposium on Information and Communication Technology","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/A5005248078","display_name":"Quang Tien Duong","orcid":"https://orcid.org/0000-0003-2575-5701"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Quang Tien Duong","raw_affiliation_strings":["vlsp, VTCC, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0003-2575-5701","affiliations":[{"raw_affiliation_string":"vlsp, VTCC, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019397372","display_name":"Duc Huy Nguyen","orcid":"https://orcid.org/0000-0003-0215-687X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc Huy Nguyen","raw_affiliation_strings":["VTCC, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0003-0215-687X","affiliations":[{"raw_affiliation_string":"VTCC, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004837969","display_name":"Ta Bao Thang","orcid":"https://orcid.org/0000-0003-0167-1263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao Thang Ta","raw_affiliation_strings":["VTCC, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0003-0167-1263","affiliations":[{"raw_affiliation_string":"VTCC, Viet Nam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064078570","display_name":"Nhat Minh Le","orcid":"https://orcid.org/0000-0002-2498-9314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nhat Minh Le","raw_affiliation_strings":["VTCC, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0002-2498-9314","affiliations":[{"raw_affiliation_string":"VTCC, Viet Nam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051897589","display_name":"Van Hai","orcid":"https://orcid.org/0000-0002-9554-5171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Hai Do","raw_affiliation_strings":["VTCC, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0002-9554-5171","affiliations":[{"raw_affiliation_string":"VTCC, Viet Nam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005248078"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1488,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42128085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"270","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.8343877792358398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6181217432022095},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6169134974479675},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.611043393611908},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5808306336402893},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5011930465698242},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5000829696655273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49484795331954956},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4774623215198517},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4219430088996887},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42118698358535767},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.42017272114753723},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.35476571321487427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32001248002052307},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3083741068840027},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2822091281414032},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11397141218185425},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08114162087440491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343877792358398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6181217432022095},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6169134974479675},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.611043393611908},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5808306336402893},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5011930465698242},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5000829696655273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49484795331954956},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4774623215198517},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4219430088996887},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42118698358535767},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.42017272114753723},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.35476571321487427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32001248002052307},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3083741068840027},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2822091281414032},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11397141218185425},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08114162087440491},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3568562.3568645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568562.3568645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 11th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2591013610","https://openalex.org/W2794506738","https://openalex.org/W2888786729","https://openalex.org/W2963604492","https://openalex.org/W2972786657","https://openalex.org/W2998702515","https://openalex.org/W3007227084","https://openalex.org/W3010679143","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3095602948","https://openalex.org/W3097777922","https://openalex.org/W3128661784","https://openalex.org/W3162391496","https://openalex.org/W3162472933","https://openalex.org/W3196974791","https://openalex.org/W3201143670","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W4221154745","https://openalex.org/W4287812705","https://openalex.org/W6776700526","https://openalex.org/W6784694379"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2109142991","https://openalex.org/W2620660273","https://openalex.org/W46679383","https://openalex.org/W2619911963","https://openalex.org/W1781713806","https://openalex.org/W2350061705","https://openalex.org/W2014474048","https://openalex.org/W1911859126","https://openalex.org/W642007152"],"abstract_inverted_index":{"Self-supervised":[0],"contrastive":[1],"learning":[2],"has":[3,80],"drawn":[4],"much":[5],"attention":[6],"due":[7],"to":[8,64,84,99],"its":[9],"stunning":[10],"performance":[11,94],"in":[12,19,89,95],"speech":[13],"and":[14,43,92],"audio":[15,25,49,91],"processing.":[16],"Recent":[17],"works":[18],"music":[20],"information":[21],"retrieval":[22],"(MIR)":[23],"or":[24],"classification":[26],"tasks":[27],"also":[28],"adopted":[29],"this":[30,67],"paradigm.":[31],"However,":[32],"most":[33],"existing":[34],"MIR":[35],"frameworks":[36],"construct":[37],"their":[38],"pipeline":[39],"with":[40,66],"augmented-segmented":[41],"training":[42],"use":[44],"convolution-based":[45],"architecture;":[46],"therefore,":[47],"the":[48,85,101],"sequential":[50,102],"correlations":[51],"are":[52],"collapsed.":[53],"This":[54],"paper":[55],"proposes":[56],"a":[57,60],"method":[58],"using":[59],"Conformer-based":[61],"encoder-projector":[62],"model":[63,79,88],"deal":[65],"problem.":[68],"The":[69],"experiments":[70,97],"conducted":[71],"on":[72],"various":[73],"test":[74],"instances":[75],"showed":[76],"that":[77],"our":[78],"competitive":[81],"results":[82],"compared":[83],"state-of-the-art":[86],"convolution":[87],"normal-speed":[90],"superior":[93],"speed-perturbed":[96],"thanks":[98],"preserving":[100],"context":[103],"ratio":[104],"distribution.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}