{"id":"https://openalex.org/W2982223350","doi":"https://doi.org/10.1109/icassp40776.2020.9054458","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","display_name":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982223350","doi":"https://doi.org/10.1109/icassp40776.2020.9054458","mag":"2982223350"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.12638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018050919","display_name":"Andy T. Liu","orcid":"https://orcid.org/0000-0002-2502-3992"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Andy T. Liu","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078898845","display_name":"Shu-Wen Yang","orcid":"https://orcid.org/0000-0001-5503-9410"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shu-wen Yang","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069156649","display_name":"Po-Han Chi","orcid":"https://orcid.org/0000-0001-8183-3781"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Han Chi","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034235870","display_name":"Po\u2010Chun Hsu","orcid":"https://orcid.org/0000-0002-6509-9377"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-chun Hsu","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018050919"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":40.5917,"has_fulltext":false,"cited_by_count":351,"citation_normalized_percentile":{"value":0.99856301,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6419","last_page":"6423"},"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.8111319541931152},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7632584571838379},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7471115589141846},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6994378566741943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6080102920532227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5544940233230591},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5412094593048096},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.46308332681655884},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4124201536178589},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33074915409088135},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32879626750946045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3236180543899536},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07033759355545044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111319541931152},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7632584571838379},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7471115589141846},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6994378566741943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6080102920532227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544940233230591},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5412094593048096},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.46308332681655884},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4124201536178589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33074915409088135},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32879626750946045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3236180543899536},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07033759355545044},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.12638","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12638","pdf_url":"https://arxiv.org/pdf/1910.12638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.12638","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12638","pdf_url":"https://arxiv.org/pdf/1910.12638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2095705004","https://openalex.org/W2270070752","https://openalex.org/W2336585117","https://openalex.org/W2613904329","https://openalex.org/W2626778328","https://openalex.org/W2747874407","https://openalex.org/W2787560479","https://openalex.org/W2842511635","https://openalex.org/W2883409523","https://openalex.org/W2896457183","https://openalex.org/W2943493972","https://openalex.org/W2947445680","https://openalex.org/W2962739339","https://openalex.org/W2963425185","https://openalex.org/W2963571336","https://openalex.org/W2964089206","https://openalex.org/W2965373594","https://openalex.org/W2972451902","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2975059944","https://openalex.org/W2979476256","https://openalex.org/W2996383576","https://openalex.org/W2996428491","https://openalex.org/W2998649947","https://openalex.org/W3037932933","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6607333740","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4389518428","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W3163689946","https://openalex.org/W4287890939","https://openalex.org/W2033364610","https://openalex.org/W2797776314"],"abstract_inverted_index":{"We":[0],"present":[1],"Mockingjay":[2,40,58,84],"as":[3],"a":[4,17,63,105],"new":[5],"speech":[6,24],"representation":[7,25,59],"learning":[8],"approach,":[9],"where":[10],"bidirectional":[11],"Transformer":[12],"encoders":[13],"are":[14],"pre-trained":[15],"on":[16,30,51,77],"large":[18],"amount":[19],"of":[20,66,112,119],"unlabeled":[21],"speech.":[22],"Previous":[23],"methods":[26],"learn":[27],"through":[28,48],"conditioning":[29,50],"past":[31,53],"frames":[32],"and":[33,54,74,88],"predicting":[34],"information":[35],"about":[36],"future":[37,55],"frames.":[38],"Whereas":[39],"is":[41,85],"designed":[42],"to":[43],"predict":[44],"the":[45,117],"current":[46],"frame":[47],"jointly":[49],"both":[52],"contexts.":[56],"The":[57],"improves":[60],"performance":[61,102],"for":[62],"wide":[64],"range":[65],"downstream":[67,93],"tasks,":[68],"including":[69],"phoneme":[70],"classification,":[71],"speaker":[72],"recognition,":[73],"sentiment":[75],"classification":[76],"spoken":[78],"content,":[79],"while":[80],"outperforming":[81],"other":[82],"approaches.":[83],"empirically":[86],"powerful":[87],"can":[89],"be":[90],"fine-tuned":[91],"with":[92,95,109],"models,":[94],"only":[96,110],"2":[97],"epochs":[98],"we":[99,115],"further":[100],"improve":[101],"dramatically.":[103],"In":[104],"low":[106],"resource":[107],"setting":[108],"0.1%":[111],"labeled":[113,125],"data,":[114],"outperform":[116],"result":[118],"Mel-features":[120],"that":[121],"uses":[122],"all":[123],"100%":[124],"data.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":79},{"year":2022,"cited_by_count":75},{"year":2021,"cited_by_count":105},{"year":2020,"cited_by_count":37},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-11-01T00:00:00"}