{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-representation-learning/papers/2","list_of":"/task/speech-representation-learning","task":"Speech Representation Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,131],"of":131,"counts":{"archive_papers_tagged":131,"with_a_code_link":48,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":131,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speech-representation-learning","prev":"/task/speech-representation-learning","next":null,"papers":[{"url":null,"slug":"language-adaptive-cross-lingual-speech","title":"Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks","date":"2022-03-09","arxiv_id":"2203.04583","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-brief-overview-of-unsupervised-neural","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","date":"2022-03-01","arxiv_id":"2203.01829","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-noise-robust-self-supervised-pre-training","title":"A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition","date":"2022-01-22","arxiv_id":"2201.08930","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-paradigm-for-articulatory-speech","title":"A Deep Paradigm for Articulatory Speech Representation Learning via Neural Convolutive Sparse Matrix Factorization","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speech-representation-learning-via","title":"Robust Speech Representation Learning via Flow-based Embedding Regularization","date":"2021-12-07","arxiv_id":"2112.03454","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-the-adversarial-vulnerability","title":"Characterizing the adversarial vulnerability of speech self-supervised learning","date":"2021-11-08","arxiv_id":"2111.04330","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-noise-robustness-of-contrastive","title":"Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction","date":"2021-10-28","arxiv_id":"2110.15430","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-representation-learning-through-self","title":"Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning","date":"2021-10-18","arxiv_id":"2110.09930","repositories_listed":0,"syntology":null},{"url":"/paper/conformer-based-self-supervised-learning-for","slug":"conformer-based-self-supervised-learning-for","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","date":"2021-10-14","arxiv_id":"2110.07313","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-wav2vec2-an-application-of","title":"An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning","date":"2021-07-26","arxiv_id":"2107.13530","repositories_listed":0,"syntology":null},{"url":null,"slug":"parp-prune-adjust-and-re-prune-for-self","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","date":"2021-06-10","arxiv_id":"2106.05933","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-representation-learning-1","title":"Unsupervised Speech Representation Learning for Behavior Modeling using Triplet Enhanced Contextualized Networks","date":"2021-04-01","arxiv_id":"2104.03899","repositories_listed":0,"syntology":null},{"url":null,"slug":"wav2vec-c-a-self-supervised-model-for-speech","title":"Wav2vec-C: A Self-supervised Model for Speech Representation Learning","date":"2021-03-09","arxiv_id":"2103.08393","repositories_listed":0,"syntology":null},{"url":null,"slug":"atcspeechnet-a-multilingual-end-to-end-speech","title":"ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems","date":"2021-02-17","arxiv_id":"2102.08535","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-purpose-speech-representation","title":"General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework","date":"2021-02-03","arxiv_id":"2102.01930","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarially-learning-disentangled-speech","title":"Adversarially learning disentangled speech representations for robust multi-factor voice conversion","date":"2021-01-30","arxiv_id":"2102.00184","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-wav2vec-2-0-on-speaker-verification","title":"Exploring wav2vec 2.0 on speaker verification and language identification","date":"2020-12-11","arxiv_id":"2012.06185","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-discrete-latent-variable","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","date":"2020-10-24","arxiv_id":"2010.14230","repositories_listed":0,"syntology":null},{"url":null,"slug":"similarity-analysis-of-self-supervised-speech","title":"Similarity Analysis of Self-Supervised Speech Representations","date":"2020-10-22","arxiv_id":"2010.11481","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-contrastive-video-speech","title":"Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound","date":"2020-08-14","arxiv_id":"2008.06607","repositories_listed":0,"syntology":null},{"url":null,"slug":"hand-crafted-attention-is-all-you-need-a","title":"Input-independent Attention Weights Are Expressive Enough: A Study of Attention in Self-supervised Audio Transformers","date":"2020-06-09","arxiv_id":"2006.05174","repositories_listed":0,"syntology":null},{"url":null,"slug":"cstnet-contrastive-speech-translation-network","title":"CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning","date":"2020-06-04","arxiv_id":"2006.02814","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-convolutional-deep-markov-model-for","title":"A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning","date":"2020-06-03","arxiv_id":"2006.02547","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-visual-self-supervision-improve-learning","title":"Does Visual Self-Supervision Improve Learning of Speech Representations for Emotion Recognition?","date":"2020-05-04","arxiv_id":"2005.01400","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-and-multilingual-speech","title":"Learning Robust and Multilingual Speech Representations","date":"2020-01-29","arxiv_id":"2001.11128","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-representation-learning-in-speech","title":"Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends","date":"2020-01-02","arxiv_id":"2001.00378","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unsupervised-speech-recognition-and","title":"Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning","date":"2019-10-28","arxiv_id":"1910.12729","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-xlnet-unsupervised-acoustic-model","title":"Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks","date":"2019-10-23","arxiv_id":"1910.10387","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-adversarial-training-and","title":"Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling","date":"2019-06-17","arxiv_id":"1906.07234","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-unsupervised-subword-modeling-via","title":"Improving Unsupervised Subword Modeling via Disentangled Speech Representation Learning and Transformation","date":"2019-06-17","arxiv_id":"1906.07245","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-learning-fine-grained-disentangled","title":"Towards Learning Fine-Grained Disentangled Representations from Speech","date":"2018-08-08","arxiv_id":"1808.02939","repositories_listed":0,"syntology":null}],"record_sha256":"eb4fbd20d2e18462b8053aafea29251283226d23fdb300c4263c564c2333fc41","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}