{"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","name":"Speech Representation Learning","slug":"speech-representation-learning","description_markdown":null,"categories":[{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":131,"papers_with_code":48,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":131,"of_with_code":48,"tagged_in_all":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"},"items":[{"url":"/paper/hubert-self-supervised-speech-representation","slug":"hubert-self-supervised-speech-representation","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","date":"2021-06-14","arxiv_id":"2106.07447","repositories_listed":11,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hubert-self-supervised-speech-representation#ran","syntology_url":"https://syntology.ai/paper/2106.07447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07447"}},"official":{"repos":["pytorch/fairseq","huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mockingjay-unsupervised-speech-representation","slug":"mockingjay-unsupervised-speech-representation","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","date":"2019-10-25","arxiv_id":"1910.12638","repositories_listed":7,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mockingjay-unsupervised-speech-representation#ran","syntology_url":"https://syntology.ai/paper/1910.12638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12638"}},"official":{"repos":["andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unispeech-sat-universal-speech-representation","slug":"unispeech-sat-universal-speech-representation","title":"UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training","date":"2021-10-12","arxiv_id":"2110.05752","repositories_listed":5,"syntology":null},{"url":"/paper/unispeech-unified-speech-representation","slug":"unispeech-unified-speech-representation","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","date":"2021-01-19","arxiv_id":"2101.07597","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unispeech-unified-speech-representation#ran","syntology_url":"https://syntology.ai/paper/2101.07597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.07597"}},"official":{"repos":["cywang97/unispeech"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/unsupervised-speech-representation-learning","slug":"unsupervised-speech-representation-learning","title":"Unsupervised speech representation learning using WaveNet autoencoders","date":"2019-01-25","arxiv_id":"1901.08810","repositories_listed":5,"syntology":null},{"url":"/paper/w2v-bert-combining-contrastive-learning-and","slug":"w2v-bert-combining-contrastive-learning-and","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","date":"2021-08-07","arxiv_id":"2108.06209","repositories_listed":4,"syntology":null},{"url":"/paper/an-unsupervised-autoregressive-model-for","slug":"an-unsupervised-autoregressive-model-for","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","date":"2019-04-05","arxiv_id":"1904.03240","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-unsupervised-autoregressive-model-for#ran","syntology_url":"https://syntology.ai/paper/1904.03240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.03240"}},"official":null}},{"url":"/paper/ernie-sat-speech-and-text-joint-pretraining-1","slug":"ernie-sat-speech-and-text-joint-pretraining-1","title":"ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech","date":"2022-11-07","arxiv_id":"2211.03545","repositories_listed":2,"syntology":null},{"url":"/paper/a-3-t-alignment-aware-acoustic-and-text","slug":"a-3-t-alignment-aware-acoustic-and-text","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","date":"2022-03-18","arxiv_id":"2203.09690","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-3-t-alignment-aware-acoustic-and-text#ran","syntology_url":"https://syntology.ai/paper/2203.09690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09690"}},"official":null}},{"url":"/paper/learning-audio-visual-speech-representation-1","slug":"learning-audio-visual-speech-representation-1","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","date":"2022-01-05","arxiv_id":"2201.02184","repositories_listed":2,"syntology":null},{"url":"/paper/xls-r-self-supervised-cross-lingual-speech","slug":"xls-r-self-supervised-cross-lingual-speech","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","date":"2021-11-17","arxiv_id":"2111.09296","repositories_listed":2,"syntology":null},{"url":"/paper/sampling-strategies-in-siamese-networks-for","slug":"sampling-strategies-in-siamese-networks-for","title":"Sampling strategies in Siamese Networks for unsupervised speech representation learning","date":"2018-04-30","arxiv_id":"1804.11297","repositories_listed":2,"syntology":null},{"url":"/paper/multi-task-corrupted-prediction-for-learning","slug":"multi-task-corrupted-prediction-for-learning","title":"Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation","date":"2025-01-23","arxiv_id":"2504.18539","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-corrupted-prediction-for-learning#ran","syntology_url":"https://syntology.ai/paper/2504.18539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.18539"}},"official":{"repos":["sungnyun/cav2vec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/k2ssl-a-faster-and-better-framework-for-self","slug":"k2ssl-a-faster-and-better-framework-for-self","title":"k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning","date":"2024-11-26","arxiv_id":"2411.17100","repositories_listed":1,"syntology":null},{"url":"/paper/eh-mam-easy-to-hard-masked-acoustic-modeling","slug":"eh-mam-easy-to-hard-masked-acoustic-modeling","title":"EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning","date":"2024-10-17","arxiv_id":"2410.13179","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/eh-mam-easy-to-hard-masked-acoustic-modeling#ran","syntology_url":"https://syntology.ai/paper/2410.13179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13179"}},"official":{"repos":["cs20s030/ehmam"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-syllable-discovery-based-on","slug":"self-supervised-syllable-discovery-based-on","title":"Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT","date":"2024-09-16","arxiv_id":"2409.10103","repositories_listed":1,"syntology":null},{"url":"/paper/mhubert-147-a-compact-multilingual-hubert","slug":"mhubert-147-a-compact-multilingual-hubert","title":"mHuBERT-147: A Compact Multilingual HuBERT Model","date":"2024-06-10","arxiv_id":"2406.06371","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-end-to-end-approach-to-noise","slug":"an-efficient-end-to-end-approach-to-noise","title":"An Efficient End-to-End Approach to Noise Invariant Speech Features via Multi-Task Learning","date":"2024-03-13","arxiv_id":"2403.08654","repositories_listed":1,"syntology":null},{"url":"/paper/the-effect-of-batch-size-on-contrastive-self","slug":"the-effect-of-batch-size-on-contrastive-self","title":"The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning","date":"2024-02-21","arxiv_id":"2402.13723","repositories_listed":1,"syntology":null},{"url":"/paper/clara-multilingual-contrastive-learning-for","slug":"clara-multilingual-contrastive-learning-for","title":"CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition","date":"2023-10-18","arxiv_id":"2310.11830","repositories_listed":1,"syntology":null},{"url":"/paper/must-p-srl-multi-lingual-and-unified","slug":"must-p-srl-multi-lingual-and-unified","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","date":"2023-10-17","arxiv_id":"2310.11541","repositories_listed":1,"syntology":null},{"url":"/paper/fast-hubert-an-efficient-training-framework","slug":"fast-hubert-an-efficient-training-framework","title":"Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning","date":"2023-09-25","arxiv_id":"2309.13860","repositories_listed":1,"syntology":null},{"url":"/paper/qs-tts-towards-semi-supervised-text-to-speech","slug":"qs-tts-towards-semi-supervised-text-to-speech","title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning","date":"2023-08-31","arxiv_id":"2309.00126","repositories_listed":1,"syntology":null},{"url":"/paper/dinosr-self-distillation-and-online","slug":"dinosr-self-distillation-and-online","title":"DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning","date":"2023-05-17","arxiv_id":"2305.10005","repositories_listed":1,"syntology":null},{"url":"/paper/a-multimodal-dynamical-variational","slug":"a-multimodal-dynamical-variational","title":"A multimodal dynamical variational autoencoder for audiovisual speech representation learning","date":"2023-05-05","arxiv_id":"2305.03582","repositories_listed":1,"syntology":null},{"url":"/paper/facexhubert-text-less-speech-driven-e-x","slug":"facexhubert-text-less-speech-driven-e-x","title":"FaceXHuBERT: Text-less Speech-driven E(X)pressive 3D Facial Animation Synthesis Using Self-Supervised Speech Representation Learning","date":"2023-03-09","arxiv_id":"2303.05416","repositories_listed":1,"syntology":null},{"url":"/paper/low-latency-transformers-for-speech","slug":"low-latency-transformers-for-speech","title":"A low latency attention module for streaming self-supervised speech representation learning","date":"2023-02-27","arxiv_id":"2302.13451","repositories_listed":1,"syntology":null},{"url":"/paper/structured-pruning-of-self-supervised-pre","slug":"structured-pruning-of-self-supervised-pre","title":"Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding","date":"2023-02-27","arxiv_id":"2302.14132","repositories_listed":1,"syntology":null},{"url":"/paper/mt4ssl-boosting-self-supervised-speech","slug":"mt4ssl-boosting-self-supervised-speech","title":"MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets","date":"2022-11-14","arxiv_id":"2211.07321","repositories_listed":1,"syntology":null},{"url":"/paper/data2vec-aqc-search-for-the-right-teaching","slug":"data2vec-aqc-search-for-the-right-teaching","title":"data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup","date":"2022-11-02","arxiv_id":"2211.01246","repositories_listed":1,"syntology":null},{"url":"/paper/slicer-learning-universal-audio","slug":"slicer-learning-universal-audio","title":"SLICER: Learning universal audio representations using low-resource self-supervised pre-training","date":"2022-11-02","arxiv_id":"2211.01519","repositories_listed":1,"syntology":null},{"url":"/paper/robust-data2vec-noise-robust-speech","slug":"robust-data2vec-noise-robust-speech","title":"Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning","date":"2022-10-27","arxiv_id":"2210.15324","repositories_listed":1,"syntology":null},{"url":"/paper/the-ability-of-self-supervised-speech-models","slug":"the-ability-of-self-supervised-speech-models","title":"The Efficacy of Self-Supervised Speech Models for Audio Representations","date":"2022-09-26","arxiv_id":"2209.12900","repositories_listed":1,"syntology":{"n":15,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/the-ability-of-self-supervised-speech-models#ran","syntology_url":"https://syntology.ai/paper/2209.12900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12900"}},"official":{"repos":["tony10101105/hear-2021-neurips-challenge---ntu-gura"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":13,"ran_from_kinds":["official"]}}},{"url":"/paper/transpeech-speech-to-speech-translation-with","slug":"transpeech-speech-to-speech-translation-with","title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","date":"2022-05-25","arxiv_id":"2205.12523","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-data-augmentation-selection-and","slug":"automatic-data-augmentation-selection-and","title":"Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning","date":"2022-04-08","arxiv_id":"2204.04170","repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-convolutive-matrix-factorization","slug":"deep-neural-convolutive-matrix-factorization","title":"Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition","date":"2022-04-01","arxiv_id":"2204.00465","repositories_listed":1,"syntology":null},{"url":"/paper/pada-pruning-assisted-domain-adaptation-for","slug":"pada-pruning-assisted-domain-adaptation-for","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","date":"2022-03-31","arxiv_id":"2203.16965","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pada-pruning-assisted-domain-adaptation-for#ran","syntology_url":"https://syntology.ai/paper/2203.16965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16965"}},"official":{"repos":["speech-lab-iitm/pada"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/robust-disentangled-variational-speech","slug":"robust-disentangled-variational-speech","title":"Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion","date":"2022-03-30","arxiv_id":"2203.16705","repositories_listed":1,"syntology":null},{"url":"/paper/lighthubert-lightweight-and-configurable","slug":"lighthubert-lightweight-and-configurable","title":"LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT","date":"2022-03-29","arxiv_id":"2203.15610","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/lighthubert-lightweight-and-configurable#ran","syntology_url":"https://syntology.ai/paper/2203.15610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15610"}},"official":{"repos":["mechanicalsea/lighthubert"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-self-supervised-audio-visual-speech","slug":"robust-self-supervised-audio-visual-speech","title":"Robust Self-Supervised Audio-Visual Speech Recognition","date":"2022-01-05","arxiv_id":"2201.01763","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-self-supervised-audio-visual-speech#ran","syntology_url":"https://syntology.ai/paper/2201.01763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.01763"}},"official":{"repos":["facebookresearch/av_hubert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/distilhubert-speech-representation-learning","slug":"distilhubert-speech-representation-learning","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","date":"2021-10-05","arxiv_id":"2110.01900","repositories_listed":1,"syntology":null},{"url":"/paper/pretext-tasks-selection-for-multitask-self","slug":"pretext-tasks-selection-for-multitask-self","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","date":"2021-07-01","arxiv_id":"2107.00594","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pretext-tasks-selection-for-multitask-self#ran","syntology_url":"https://syntology.ai/paper/2107.00594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00594"}},"official":{"repos":["salah-zaiem/PL-groupselection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/supervised-speech-representation-learning-for","slug":"supervised-speech-representation-learning-for","title":"Supervised Speech Representation Learning for Parkinson's Disease Classification","date":"2021-06-01","arxiv_id":"2106.00531","repositories_listed":1,"syntology":null},{"url":"/paper/using-radio-archives-for-low-resource-speech","slug":"using-radio-archives-for-low-resource-speech","title":"Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users","date":"2021-04-27","arxiv_id":"2104.13083","repositories_listed":1,"syntology":null},{"url":"/paper/conditional-independence-for-pretext-task","slug":"conditional-independence-for-pretext-task","title":"Conditional independence for pretext task selection in Self-supervised speech representation learning","date":"2021-04-15","arxiv_id":"2104.07388","repositories_listed":1,"syntology":null},{"url":"/paper/fast-development-of-asr-in-african-languages","slug":"fast-development-of-asr-in-african-languages","title":"Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning","date":"2021-03-16","arxiv_id":"2103.08993","repositories_listed":1,"syntology":null},{"url":"/paper/decoar-2-0-deep-contextualized-acoustic","slug":"decoar-2-0-deep-contextualized-acoustic","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","date":"2020-12-11","arxiv_id":"2012.06659","repositories_listed":1,"syntology":null},{"url":"/paper/speech-simclr-combining-contrastive-and","slug":"speech-simclr-combining-contrastive-and","title":"Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning","date":"2020-10-27","arxiv_id":"2010.13991","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speech-simclr-combining-contrastive-and#ran","syntology_url":"https://syntology.ai/paper/2010.13991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13991"}},"official":{"repos":["athena-team/athena"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":null,"slug":"hyfuse-aligning-heterogeneous-speech-pre","title":"HYFuse: Aligning Heterogeneous Speech Pre-Trained Representations in Hyperbolic Space for Speech Emotion Recognition","date":"2025-06-03","arxiv_id":"2506.03403","repositories_listed":0,"syntology":null},{"url":null,"slug":"durep-dual-mode-speech-representation","title":"DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation","date":"2025-05-26","arxiv_id":"2505.19774","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-semantic-disentangled-privacy","title":"Universal Semantic Disentangled Privacy-preserving Speech Representation Learning","date":"2025-05-19","arxiv_id":"2505.13085","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniwav-towards-unified-pre-training-for","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","date":"2025-03-02","arxiv_id":"2503.00733","repositories_listed":0,"syntology":null},{"url":null,"slug":"jooci-a-framework-for-learning-comprehensive","title":"JOOCI: a Framework for Learning Comprehensive Speech Representations","date":"2024-10-14","arxiv_id":"2410.11086","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-music-foundation-models-better-at-singing","title":"Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models","date":"2024-09-21","arxiv_id":"2409.14131","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-residual-extraction-based-pre","title":"Progressive Residual Extraction based Pre-training for Speech Representation Learning","date":"2024-08-31","arxiv_id":"2409.00387","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-representation-learning-revisited-the","title":"Speech Representation Learning Revisited: The Necessity of Separate Learnable Parameters and Robust Data Augmentation","date":"2024-08-20","arxiv_id":"2408.10557","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-the-next-frontier-in-speech","title":"Towards the Next Frontier in Speech Representation Learning Using Disentanglement","date":"2024-07-02","arxiv_id":"2407.02543","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-speech-representation-learning","title":"Towards Robust Speech Representation Learning for Thousands of Languages","date":"2024-06-30","arxiv_id":"2407.00837","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotion-aware-speech-self-supervised","title":"Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge","date":"2024-06-10","arxiv_id":"2406.06646","repositories_listed":0,"syntology":null},{"url":null,"slug":"xlavs-r-cross-lingual-audio-visual-speech","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","date":"2024-03-21","arxiv_id":"2403.14402","repositories_listed":0,"syntology":null},{"url":null,"slug":"unit-dsr-dysarthric-speech-reconstruction","title":"UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization","date":"2024-01-26","arxiv_id":"2401.14664","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-self-supervised-learning-of-speech","title":"Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspective","date":"2024-01-16","arxiv_id":"2401.08833","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiency-oriented-approaches-for-self","title":"Efficiency-oriented approaches for self-supervised speech representation learning","date":"2023-12-18","arxiv_id":"2312.11142","repositories_listed":0,"syntology":null},{"url":null,"slug":"reimagining-speech-a-scoping-review-of-deep","title":"Reimagining Speech: A Scoping Review of Deep Learning-Powered Voice Conversion","date":"2023-11-14","arxiv_id":"2311.08104","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-disentangled-speech-representations","title":"Learning Disentangled Speech Representations","date":"2023-11-04","arxiv_id":"2311.03389","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-representation-learning-1","title":"Privacy-preserving Representation Learning for Speech Understanding","date":"2023-10-26","arxiv_id":"2310.17194","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-hubert-self-supervised-spatial-speech","title":"Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio","date":"2023-10-17","arxiv_id":"2310.10922","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-self-supervised-speech","title":"Evaluating Self-Supervised Speech Representations for Indigenous American Languages","date":"2023-10-05","arxiv_id":"2310.03639","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-representation-learning-learning","title":"Speech representation learning: Learning bidirectional encoders with single-view, multi-view, and multi-task methods","date":"2023-07-25","arxiv_id":"2308.00129","repositories_listed":0,"syntology":null},{"url":null,"slug":"masr-metadata-aware-speech-representation","title":"MASR: Multi-label Aware Speech Representation","date":"2023-07-20","arxiv_id":"2307.10982","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-device-constrained-self-supervised-speech","title":"On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation","date":"2023-07-06","arxiv_id":"2307.02720","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowchase-a-mobile-application-for","title":"Flowchase: a Mobile Application for Pronunciation Training","date":"2023-07-05","arxiv_id":"2307.02051","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-aware-speech-representation-learning","title":"Label Aware Speech Representation Learning For Language Identification","date":"2023-06-07","arxiv_id":"2306.04374","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-or-sequential-training-how","title":"Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System","date":"2023-06-05","arxiv_id":"2306.02972","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-on-speech-restoration","title":"An empirical study on speech restoration guided by self supervised speech representation","date":"2023-05-30","arxiv_id":"2305.18739","repositories_listed":0,"syntology":null},{"url":null,"slug":"intapt-information-theoretic-adversarial","title":"INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition","date":"2023-05-25","arxiv_id":"2305.16371","repositories_listed":0,"syntology":null},{"url":null,"slug":"tranusr-phoneme-to-word-transcoder-based","title":"TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition","date":"2023-05-23","arxiv_id":"2305.13629","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cross-lingual-visual-speech","title":"Learning Cross-lingual Visual Speech Representations","date":"2023-03-14","arxiv_id":"2303.09455","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-speech-representation-1","title":"Self-supervised speech representation learning for keyword-spotting with light-weight transformers","date":"2023-03-07","arxiv_id":"2303.04255","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-speech-representation-learning-with","title":"Efficient Speech Representation Learning with Low-Bit Quantization","date":"2022-12-14","arxiv_id":"2301.00652","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-self-supervised-multilingual-speech","title":"Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information","date":"2022-12-07","arxiv_id":"2212.03476","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-feature-learning-for-real-time","title":"Disentangled Feature Learning for Real-Time Neural Speech Coding","date":"2022-11-22","arxiv_id":"2211.11960","repositories_listed":0,"syntology":null},{"url":null,"slug":"vatlm-visual-audio-text-pre-training-with","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","date":"2022-11-21","arxiv_id":"2211.11275","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-robustness-of-distilhubert-to","title":"Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement","date":"2022-11-12","arxiv_id":"2211.06562","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-knowledge-distillation-to","title":"Application of Knowledge Distillation to Multi-task Speech Representation Learning","date":"2022-10-29","arxiv_id":"2210.16611","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-speech-representation-learning-1","title":"Disentangled Speech Representation Learning for One-Shot Cross-lingual Voice Conversion Using $β$-VAE","date":"2022-10-25","arxiv_id":"2210.13771","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speech-representation-learning-via","title":"Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach","date":"2022-10-25","arxiv_id":"2210.13805","repositories_listed":0,"syntology":null},{"url":null,"slug":"superb-slt-2022-challenge-on-generalization","title":"SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning","date":"2022-10-16","arxiv_id":"2210.08634","repositories_listed":0,"syntology":null},{"url":null,"slug":"hubert-tr-reviving-turkish-automatic-speech","title":"Experiments on Turkish ASR with Self-Supervised Speech Representation Learning","date":"2022-10-13","arxiv_id":"2210.07323","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-use-of-semantically-aligned-speech","title":"On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding","date":"2022-10-11","arxiv_id":"2210.05291","repositories_listed":0,"syntology":null},{"url":null,"slug":"utts-unsupervised-tts-with-conditional","title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","date":"2022-06-06","arxiv_id":"2206.02512","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-models-of-audio-effectively","title":"Self-supervised models of audio effectively explain human cortical responses to speech","date":"2022-05-27","arxiv_id":"2205.14252","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-speech-representation","title":"Self-Supervised Speech Representation Learning: A Review","date":"2022-05-21","arxiv_id":"2205.10643","repositories_listed":0,"syntology":null},{"url":null,"slug":"samu-xlsr-semantically-aligned-multimodal","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","date":"2022-05-17","arxiv_id":"2205.08180","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-pronunciation-assessment-using-self","title":"Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning","date":"2022-04-08","arxiv_id":"2204.03863","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-speech-representation-learning","title":"Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective","date":"2022-04-05","arxiv_id":"2204.02166","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speaker-recognition-with-transformers","title":"Robust Speaker Recognition with Transformers Using wav2vec 2.0","date":"2022-03-28","arxiv_id":"2203.15095","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-unsupervised-and-weakly-supervised","title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","date":"2022-03-24","arxiv_id":"2203.13339","repositories_listed":0,"syntology":null},{"url":null,"slug":"xtreme-s-evaluating-cross-lingual-speech","title":"XTREME-S: Evaluating Cross-lingual Speech Representations","date":"2022-03-21","arxiv_id":"2203.10752","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-speech-representation","title":"Privacy-Preserving Speech Representation Learning using Vector Quantization","date":"2022-03-15","arxiv_id":"2203.09518","repositories_listed":0,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/task/speech-representation-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/speech-representation-learning/papers/2","json":"/task/speech-representation-learning/papers/2.json","rows":31},{"order":"ran","page":1,"of":1,"url":"/task/speech-representation-learning/papers/ran/1","json":"/task/speech-representation-learning/papers/ran/1.json","rows":13}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"16b55a630c73cabaeeef2bc5bbf8c0331ef2344e2ebb9ce60cec312b7ea8a82b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}