{"id":"https://openalex.org/W3160016036","doi":"https://doi.org/10.1109/icassp39728.2021.9414996","title":"Transformer Based Unsupervised Pre-Training for Acoustic Representation Learning","display_name":"Transformer Based Unsupervised Pre-Training for Acoustic Representation Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160016036","doi":"https://doi.org/10.1109/icassp39728.2021.9414996","mag":"3160016036"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5029228290","display_name":"Ruixiong Zhang","orcid":"https://orcid.org/0000-0002-8597-8969"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruixiong Zhang","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079117782","display_name":"Haiwei Wu","orcid":"https://orcid.org/0000-0001-8807-0254"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwei Wu","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050050390","display_name":"Wubo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wubo Li","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110582135","display_name":"Dongwei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongwei Jiang","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808317","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4307-5355"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029228290"],"corresponding_institution_ids":["https://openalex.org/I4401726870"],"apc_list":null,"apc_paid":null,"fwci":2.5902,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90236646,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6933","last_page":"6937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.778389036655426},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6889296770095825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6669079065322876},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5683420896530151},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5387229919433594},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4549039304256439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4491285979747772},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4344732463359833},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3941706717014313},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07904359698295593},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06577309966087341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778389036655426},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6889296770095825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6669079065322876},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5683420896530151},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5387229919433594},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4549039304256439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4491285979747772},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4344732463359833},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3941706717014313},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07904359698295593},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06577309966087341},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1568716973","https://openalex.org/W2052666245","https://openalex.org/W2062170755","https://openalex.org/W2101105183","https://openalex.org/W2146334809","https://openalex.org/W2533262878","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2936451900","https://openalex.org/W2962784628","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2972943112","https://openalex.org/W2973048981","https://openalex.org/W2981991061","https://openalex.org/W3015707499","https://openalex.org/W3036237438","https://openalex.org/W3037217258","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6729014267","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6769238691","https://openalex.org/W6776039324","https://openalex.org/W6779574021","https://openalex.org/W6844194202","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165"],"abstract_inverted_index":{"Recently,":[0],"a":[1,37,84],"variety":[2],"of":[3,54],"acoustic":[4,12,45,55],"tasks":[5],"and":[6,39,63,91,125,144],"related":[7],"applications":[8],"arised.":[9],"For":[10,108,130],"many":[11],"tasks,":[13],"the":[14,67,81,98,112,133],"labeled":[15],"data":[16,77,87],"size":[17],"may":[18],"be":[19],"limited.":[20],"To":[21],"handle":[22],"this":[23],"problem,":[24],"we":[25],"propose":[26],"an":[27],"unsupervised":[28],"pre-training":[29,72,86],"method":[30],"using":[31,73],"Transformer":[32],"based":[33],"encoder":[34],"to":[35],"learn":[36],"general":[38],"robust":[40],"high-level":[41],"representation":[42],"for":[43,94],"all":[44],"tasks.":[46],"Experiments":[47],"have":[48,69],"been":[49],"conducted":[50],"on":[51,105,120,127,141,146],"three":[52],"kinds":[53],"tasks:":[56],"speech":[57,64,95,131],"emotion":[58,96],"recognition,":[59,97],"sound":[60,109],"event":[61,110],"detection":[62],"translation.":[65],"All":[66],"experiments":[68],"shown":[70],"that":[71],"its":[74],"own":[75],"training":[76],"can":[78,100,115,136],"significantly":[79],"improve":[80,102,117,138],"performance.":[82],"With":[83],"larger":[85],"combining":[88],"MuST-C,":[89],"Librispeech":[90],"ESC-US":[92],"datasets,":[93],"UAR":[99],"further":[101,116,137],"absolutely":[103,118],"4.3%":[104],"IEMOCAP":[106],"dataset.":[107,148],"detection,":[111],"F1":[113],"score":[114,135],"1.5%":[119],"DCASE2018":[121],"task5":[122],"development":[123],"set":[124],"2.1%":[126],"evaluation":[128],"set.":[129],"translation,":[132],"BLEU":[134],"relatively":[139],"12.2%":[140],"En-De":[142],"dataset":[143],"8.4%":[145],"En-Fr":[147]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
