{"total":126,"rows":[{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657,"area":null},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666,"area":null},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601,"area":null},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312,"area":null},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221,"area":null},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213,"area":null},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169,"area":null},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144,"area":null},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106,"area":null},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82,"area":null},{"id":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82,"area":null},{"id":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81,"area":null},{"id":"2101.07597","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","created":"2021-01-19","cited_by_count":77,"area":null},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77,"area":null},{"id":"2204.09224","title":"ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers","created":"2022-04-20","cited_by_count":74,"area":null},{"id":"2111.10367","title":"SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech","created":"2021-11-19","cited_by_count":72,"area":null},{"id":"2406.06371","title":"mHuBERT-147: A Compact Multilingual HuBERT Model","created":"2024-06-10","cited_by_count":66,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2209.15329","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","created":"2022-09-30","cited_by_count":49,"area":null},{"id":"2303.16535","title":"Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning","created":"2023-03-29","cited_by_count":48,"area":null},{"id":"2212.06246","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","created":"2022-12-12","cited_by_count":47,"area":null},{"id":"2110.05752","title":"UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training","created":"2021-10-12","cited_by_count":45,"area":null},{"id":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","cited_by_count":44,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"area":null},{"id":"2210.02016","title":"Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization","created":"2022-10-05","cited_by_count":35,"area":null},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"area":null},{"id":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29,"area":null},{"id":"2303.08737","title":"Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022","created":"2023-03-15","cited_by_count":29,"area":null},{"id":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27,"area":null},{"id":"2204.03417","title":"Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0","created":"2022-04-07","cited_by_count":27,"area":null},{"id":"2110.00165","title":"Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning","created":"2021-10-01","cited_by_count":26,"area":null},{"id":"2210.08634","title":"SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning","created":"2022-10-16","cited_by_count":26,"area":null},{"id":"2103.08393","title":"Wav2vec-C: A Self-supervised Model for Speech Representation Learning","created":"2021-03-09","cited_by_count":25,"area":null},{"id":"2202.03543","title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling","created":"2022-02-07","cited_by_count":25,"area":null},{"id":"2406.17376","title":"Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection","created":"2024-06-25","cited_by_count":25,"area":null},{"id":"2205.05173","title":"Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook","created":"2022-05-10","cited_by_count":24,"area":null},{"id":"2404.02098","title":"BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition","created":"2024-04-02","cited_by_count":21,"area":null},{"id":"2103.10731","title":"Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation","created":"2021-03-19","cited_by_count":19,"area":null},{"id":"2102.03229","title":"Multi-Task Self-Supervised Pre-Training for Music Classification","created":"2021-02-05","cited_by_count":18,"area":null},{"id":"2201.00464","title":"Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection","created":"2022-01-03","cited_by_count":18,"area":null},{"id":"2309.05472","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","created":"2023-09-11","cited_by_count":18,"area":null},{"id":"2203.16104","title":"Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation","created":"2022-03-30","cited_by_count":17,"area":null},{"id":"2308.14456","title":"Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads","created":"2023-08-28","cited_by_count":17,"area":null},{"id":"2110.04934","title":"Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition","created":"2021-10-11","cited_by_count":16,"area":null},{"id":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2112.08778","title":"Self-Supervised Learning for speech recognition with Intermediate layer supervision","created":"2021-12-16","cited_by_count":15,"area":null},{"id":"2207.00952","title":"M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation","created":"2022-07-03","cited_by_count":15,"area":null},{"id":"2303.06740","title":"Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study","created":"2023-03-12","cited_by_count":15,"area":null},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","cited_by_count":14,"area":null},{"id":"2110.15430","title":"Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2308.06112","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","created":"2023-08-11","cited_by_count":12,"area":null},{"id":"2410.14389","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2401.02746","title":"Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2204.02804","title":"Federated Self-supervised Speech Representations: Are We There Yet?","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2208.05445","title":"Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech","created":"2022-08-10","cited_by_count":10,"area":null},{"id":"2306.01015","title":"How to Estimate Model Transferability of Pre-Trained Speech Models?","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2110.07336","title":"RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training","created":"2021-10-08","cited_by_count":9,"area":null},{"id":"2207.04356","title":"A Comparative Study of Self-supervised Speech Representation Based Voice Conversion","created":"2022-07-10","cited_by_count":9,"area":null},{"id":"2205.07390","title":"Learning Representations for New Sound Classes With Continual Self-Supervised Learning","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2211.07321","title":"MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2107.00594","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2109.13921","title":"Click-through Rate Prediction with Auto-Quantized Contrastive Learning","created":"2021-09-27","cited_by_count":7,"area":null},{"id":"2211.01522","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2206.05518","title":"Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition","created":"2022-06-11","cited_by_count":6,"area":null},{"id":"2209.12900","title":"The Efficacy of Self-Supervised Speech Models for Audio Representations","created":"2022-09-26","cited_by_count":6,"area":null},{"id":"2209.15575","title":"Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2303.01034","title":"Multi-Task Self-Supervised Time-Series Representation Learning","created":"2023-03-02","cited_by_count":6,"area":null},{"id":"2509.01548","title":"Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing","created":"2025-09-01","cited_by_count":6,"area":null},{"id":"2102.10378","title":"Self-Supervised Learning via multi-Transformation Classification for Action Recognition","created":"2021-02-20","cited_by_count":5,"area":null},{"id":"2106.15238","title":"Representation based meta-learning for few-shot spoken intent recognition","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2201.01046","title":"Sound and Visual Representation Learning with Multiple Pretraining Tasks","created":"2022-01-04","cited_by_count":5,"area":null},{"id":"2204.00352","title":"On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting","created":"2022-04-01","cited_by_count":5,"area":null},{"id":"2207.04471","title":"Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio Representation","created":"2022-07-10","cited_by_count":5,"area":null},{"id":"2307.05161","title":"On the Effectiveness of Speech Self-supervised Learning for Music","created":"2023-07-11","cited_by_count":5,"area":null},{"id":"2102.04945","title":"On permutation invariant training for speech source separation","created":"2021-02-09","cited_by_count":4,"area":null},{"id":"2110.09930","title":"Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning","created":"2021-10-18","cited_by_count":4,"area":null},{"id":"2204.04170","title":"Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning","created":"2022-04-08","cited_by_count":4,"area":null},{"id":"2206.04465","title":"Joint Encoder-Decoder Self-Supervised Pre-training for ASR","created":"2022-06-09","cited_by_count":4,"area":null},{"id":"2210.12635","title":"Quantitative Evidence on Overlooked Aspects of Enrollment Speaker Embeddings for Target Speaker Separation","created":"2022-10-23","cited_by_count":4,"area":null},{"id":"2305.08099","title":"Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations","created":"2023-05-14","cited_by_count":4,"area":null},{"id":"2103.08993","title":"Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning","created":"2021-03-16","cited_by_count":3,"area":null},{"id":"2104.07388","title":"Conditional independence for pretext task selection in Self-supervised speech representation learning","created":"2021-04-15","cited_by_count":3,"area":null},{"id":"2110.03894","title":"Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2211.02536","title":"Biased Self-supervised learning for ASR","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2305.17191","title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2103.01461","title":"Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2110.05994","title":"Word Order Does Not Matter For Speech Recognition","created":"2021-10-12","cited_by_count":2,"area":null},{"id":"2201.02305","title":"Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task","created":"2022-01-07","cited_by_count":2,"area":null},{"id":"2202.08981","title":"A Summary of the ComParE COVID-19 Challenges","created":"2022-02-17","cited_by_count":2,"area":null},{"id":"2212.03812","title":"An Overview of Indian Spoken Language Recognition from Machine Learning Perspective","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2302.13259","title":"Can we avoid Double Descent in Deep Neural Networks?","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2311.15954","title":"A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2402.01274","title":"On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2410.07530","title":"Audio Explanation Synthesis with Generative Foundation Models","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2502.01084","title":"Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2102.01930","title":"General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework","created":"2021-02-03","cited_by_count":1,"area":null}],"next_cursor":"100"}