{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mockingjay-unsupervised-speech-representation","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","arxiv_id":"1910.12638","date":"2019-10-25","proceeding":null,"authors":["Andy T. Liu","Shu-wen Yang","Po-Han Chi","Po-chun Hsu","Hung-Yi Lee"],"abstract":"We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and predicting information about future frames. Whereas Mockingjay is designed to predict the current frame through jointly conditioning on both past and future contexts. The Mockingjay representation improves performance for a wide range of downstream tasks, including phoneme classification, speaker recognition, and sentiment classification on spoken content, while outperforming other approaches. Mockingjay is empirically powerful and can be fine-tuned with downstream models, with only 2 epochs we further improve performance dramatically. In a low resource setting with only 0.1% of labeled data, we outperform the result of Mel-features that uses all 100% labeled data.","url_abs":"https://arxiv.org/abs/1910.12638v2","url_pdf":"https://arxiv.org/pdf/1910.12638v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mockingjay-unsupervised-speech-representation","repo_url":"https://github.com/andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mockingjay-unsupervised-speech-representation","repo_url":"https://github.com/592595/TERA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mockingjay-unsupervised-speech-representation","repo_url":"https://github.com/Pandade1997/tera_asvproof","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mockingjay-unsupervised-speech-representation","repo_url":"https://github.com/Vernacular-ai/Multimodal-Slu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mockingjay-unsupervised-speech-representation","repo_url":"https://github.com/joselyn-rodriguez/s3prl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mockingjay-unsupervised-speech-representation","repo_url":"https://github.com/s3prl/s3prl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mockingjay-unsupervised-speech-representation","repo_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"},{"task_slug":"speech-representation-learning","task_name":"Speech Representation Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.12638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12638"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/592595/TERA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/s3prl/s3prl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Vernacular-ai/Multimodal-Slu","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joselyn-rodriguez/s3prl","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pandade1997/tera_asvproof","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":8},"by_repo_kind":{"listed":{"samples":11,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"mockingjay/model.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/mockingjay/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"mockingjay/model.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/mockingjay/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"d30d6c3098df2c42","entry":"prune_linear_layer","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"mockingjay/model.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/mockingjay/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"code_sha256_prefix":"f9694c7c35ca4ecf","entry":"boolean_string","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"preprocess.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9694c7c35ca4ecf"}},{"code_sha256_prefix":"7157f9c69c8f6312","entry":"inv_preemphasis","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"utility/audio.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/utility/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7157f9c69c8f6312"}},{"code_sha256_prefix":"a757821419710bd3","entry":"npy2sdk","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"preprocess_mosi.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/preprocess_mosi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a757821419710bd3"}},{"code_sha256_prefix":"35551a0a794f39cb","entry":"read_text","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"preprocess.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35551a0a794f39cb"}},{"code_sha256_prefix":"a3073fde9ca15c72","entry":"read_text","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"preprocess_timit.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/preprocess_timit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3073fde9ca15c72"}},{"code_sha256_prefix":"b486ecca84243b21","entry":"sdk2npy","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"preprocess_mosi.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/preprocess_mosi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b486ecca84243b21"}},{"code_sha256_prefix":"203c15b8b298dfdb","entry":"subword_preprocess","repo":"samirsahoo007/Audio-and-Speech-Processing","repo_kind":"listed","path":"preprocess.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"203c15b8b298dfdb"}},{"code_sha256_prefix":"78826dfaa4289758","entry":"test_transformer","repo":"592595/TERA","repo_kind":"listed","path":"run_upstream.py","file_url":"https://github.com/592595/TERA/blob/HEAD/run_upstream.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78826dfaa4289758"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}