{"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/an-unsupervised-autoregressive-model-for","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","arxiv_id":"1904.03240","date":"2019-04-05","proceeding":null,"authors":["Yu-An Chung","Wei-Ning Hsu","Hao Tang","James Glass"],"abstract":"This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is designed to preserve information for a wide range of downstream tasks. In addition, the proposed model does not require any phonetic or word boundary labels, allowing the model to benefit from large quantities of unlabeled data. Speech representations learned by our model significantly improve performance on both phone classification and speaker verification over the surface features and other supervised and unsupervised approaches. Further analysis shows that different levels of speech information are captured by our model at different layers. In particular, the lower layers tend to be more discriminative for speakers, while the upper layers provide more phonetic content.","url_abs":"https://arxiv.org/abs/1904.03240v2","url_pdf":"https://arxiv.org/pdf/1904.03240v2.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":"an-unsupervised-autoregressive-model-for","repo_url":"https://github.com/andi611/Mockingjay-Speech-Representation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"an-unsupervised-autoregressive-model-for","repo_url":"https://github.com/iamyuanchung/Autoregressive-Predictive-Coding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"an-unsupervised-autoregressive-model-for","repo_url":"https://github.com/iamyuanchung/VQ-APC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"an-unsupervised-autoregressive-model-for","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":"speaker-verification","task_name":"Speaker Verification"},{"task_slug":"speech-representation-learning","task_name":"Speech Representation Learning"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.03240"}},"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/iamyuanchung/Autoregressive-Predictive-Coding","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iamyuanchung/VQ-APC","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/andi611/Mockingjay-Speech-Representation","reach":null}],"summary":{"ran_fixture":3,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":3,"samples":[{"code_sha256_prefix":"2189fca2ccc0d19e","entry":"get_mockingjay_model","repo":"andi611/Mockingjay-Speech-Representation","repo_kind":"listed","path":"runner_mockingjay.py","file_url":"https://github.com/andi611/Mockingjay-Speech-Representation/blob/HEAD/runner_mockingjay.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2189fca2ccc0d19e"}},{"code_sha256_prefix":"4763872bbaf3ab60","entry":"gumbel_softmax","repo":"iamyuanchung/VQ-APC","repo_kind":"listed","path":"vqapc_model.py","file_url":"https://github.com/iamyuanchung/VQ-APC/blob/HEAD/vqapc_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4763872bbaf3ab60"}},{"code_sha256_prefix":"4650349b06b3d90f","entry":"gumbel_softmax_sample","repo":"iamyuanchung/VQ-APC","repo_kind":"listed","path":"vqapc_model.py","file_url":"https://github.com/iamyuanchung/VQ-APC/blob/HEAD/vqapc_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4650349b06b3d90f"}},{"code_sha256_prefix":"cec667e77fe8894d","entry":"sample_gumbel","repo":"iamyuanchung/VQ-APC","repo_kind":"listed","path":"vqapc_model.py","file_url":"https://github.com/iamyuanchung/VQ-APC/blob/HEAD/vqapc_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cec667e77fe8894d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}