{"total":83,"rows":[{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342,"area":null},{"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":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169,"area":null},{"id":"2104.01027","title":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","created":"2021-04-02","cited_by_count":151,"area":null},{"id":"2110.09327","title":"Self-Supervised Representation Learning: Introduction, Advances and Challenges","created":"2021-10-18","cited_by_count":148,"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":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","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":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"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":"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":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","cited_by_count":44,"area":null},{"id":"2109.03381","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering","created":"2021-09-08","cited_by_count":39,"area":null},{"id":"2111.08137","title":"Joint Unsupervised and Supervised Training for Multilingual ASR","created":"2021-11-15","cited_by_count":39,"area":null},{"id":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2205.08180","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","created":"2022-05-17","cited_by_count":32,"area":null},{"id":"2206.02119","title":"A Multimodal Corpus for Emotion Recognition in Sarcasm","created":"2022-06-05","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":"2206.02353","title":"Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data","created":"2022-06-06","cited_by_count":27,"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":"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":"2110.15684","title":"Fusing ASR Outputs in Joint Training for Speech Emotion Recognition","created":"2021-10-29","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":"2107.13530","title":"An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning","created":"2021-07-26","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":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18,"area":null},{"id":"2409.20201","title":"AfriHuBERT: A self-supervised speech representation model for African languages","created":"2024-09-30","cited_by_count":18,"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":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","cited_by_count":14,"area":null},{"id":"2104.01604","title":"Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers","created":"2021-04-04","cited_by_count":11,"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":"2206.09783","title":"Boosting Cross-Domain Speech Recognition with Self-Supervision","created":"2022-06-20","cited_by_count":10,"area":null},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2206.13654","title":"Wav2Vec-Aug: Improved self-supervised training with limited data","created":"2022-06-27","cited_by_count":9,"area":null},{"id":"2103.02420","title":"Multi-view Audio and Music Classification","created":"2021-03-03","cited_by_count":8,"area":null},{"id":"2202.00097","title":"Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data","created":"2022-01-31","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":"2305.19011","title":"MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Models","created":"2023-05-30","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":"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":"2102.08015","title":"Improving speech recognition models with small samples for air traffic control systems","created":"2021-02-16","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":"2106.15238","title":"Representation based meta-learning for few-shot spoken intent recognition","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2111.14842","title":"Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?","created":"2021-11-29","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":"2203.11997","title":"Federated Self-Supervised Learning for Acoustic Event Classification","created":"2022-03-22","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":"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":"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":"2404.11163","title":"LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2102.00850","title":"On Scaling Contrastive Representations for Low-Resource Speech Recognition","created":"2021-02-01","cited_by_count":3,"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":"2306.15464","title":"Large-scale unsupervised audio pre-training for video-to-speech synthesis","created":"2023-06-27","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":"2104.00513","title":"Auto-KWS 2021 Challenge: Task, Datasets, and Baselines","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2109.12058","title":"Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verification","created":"2021-09-24","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},{"id":"2104.03899","title":"Unsupervised Speech Representation Learning for Behavior Modeling using Triplet Enhanced Contextualized Networks","created":"2021-04-01","cited_by_count":1,"area":null},{"id":"2307.12343","title":"Self-Supervised Learning for Audio-Based Emotion Recognition","created":"2023-07-23","cited_by_count":1,"area":null},{"id":"2310.09388","title":"CORN: Co-Trained Full- And No-Reference Speech Quality Assessment","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2403.19822","title":"Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2407.02543","title":"Towards the Next Frontier in Speech Representation Learning Using Disentanglement","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2204.04802","title":"On the pragmatism of using binary classifiers over data intensive neural network classifiers for detection of COVID-19 from voice","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2204.09227","title":"Cross-stitched Multi-modal Encoders","created":"2022-04-20","cited_by_count":0,"area":null},{"id":"2206.13365","title":"Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2210.06368","title":"Individualized Conditioning and Negative Distances for Speaker Separation","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2403.15170","title":"Exploring the Task-agnostic Trait of Self-supervised Learning in the Context of Detecting Mental Disorders","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2405.12847","title":"A Dataset and Baselines for Measuring and Predicting the Music Piece Memorability","created":"2024-05-21","cited_by_count":0,"area":null}],"next_cursor":null}