{"total":176,"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":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727,"area":null},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666,"area":null},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347,"area":null},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"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":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"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":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"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":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"id":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"area":null},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","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":"2103.12676","title":"Self-supervised representation learning from 12-lead ECG data","created":"2021-03-23","cited_by_count":80,"area":null},{"id":"2109.11680","title":"Simple and Effective Zero-shot Cross-lingual Phoneme Recognition","created":"2021-09-23","cited_by_count":79,"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":"2206.07579","title":"A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions","created":"2022-06-15","cited_by_count":73,"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":"2202.12938","title":"Assessing the State of Self-Supervised Human Activity Recognition using Wearables","created":"2022-02-22","cited_by_count":65,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"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":"2104.11462","title":"LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech","created":"2021-04-23","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":"2210.07185","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","created":"2022-10-13","cited_by_count":42,"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":"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":"2110.04590","title":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","created":"2021-10-09","cited_by_count":39,"area":null},{"id":"2205.14252","title":"Self-supervised models of audio effectively explain human cortical responses to speech","created":"2022-05-27","cited_by_count":37,"area":null},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37,"area":null},{"id":"2205.12523","title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","created":"2022-05-25","cited_by_count":34,"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":"2202.03218","title":"Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition","created":"2022-02-07","cited_by_count":32,"area":null},{"id":"2210.02595","title":"Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora","created":"2022-10-05","cited_by_count":31,"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":"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":"2202.11929","title":"Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring","created":"2022-02-24","cited_by_count":24,"area":null},{"id":"2104.03017","title":"Utilizing Self-supervised Representations for MOS Prediction","created":"2021-04-07","cited_by_count":20,"area":null},{"id":"2305.12464","title":"Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces","created":"2023-05-21","cited_by_count":20,"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":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18,"area":null},{"id":"2303.10126","title":"IRGen: Generative Modeling for Image Retrieval","created":"2023-03-17","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":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2106.00273","title":"Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning","created":"2021-06-01","cited_by_count":16,"area":null},{"id":"2211.09944","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","created":"2022-11-17","cited_by_count":16,"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":"2202.01252","title":"Speaker Normalization for Self-supervised Speech Emotion Recognition","created":"2022-02-02","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":"2212.01282","title":"CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models","created":"2022-12-01","cited_by_count":13,"area":null},{"id":"2112.13416","title":"Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings","created":"2021-12-26","cited_by_count":12,"area":null},{"id":"2203.08810","title":"Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling","created":"2022-03-15","cited_by_count":12,"area":null},{"id":"2103.08207","title":"XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition","created":"2021-03-15","cited_by_count":11,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2401.17632","title":"What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis","created":"2024-01-31","cited_by_count":11,"area":null},{"id":"2110.00678","title":"Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning","created":"2021-10-01","cited_by_count":10,"area":null},{"id":"2204.11934","title":"On-demand compute reduction with stochastic wav2vec 2.0","created":"2022-04-25","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":"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":"2110.03504","title":"Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models","created":"2021-10-07","cited_by_count":9,"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":"2305.14035","title":"Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2411.17666","title":"How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2203.15840","title":"Autoregressive Co-Training for Learning Discrete Speech Representations","created":"2022-03-29","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":"2110.08895","title":"DECAR: Deep Clustering for learning general-purpose Audio Representations","created":"2021-10-17","cited_by_count":7,"area":null},{"id":"2204.03219","title":"DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2205.03759","title":"Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information","created":"2022-05-08","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":"2212.08542","title":"Context-aware Fine-tuning of Self-supervised Speech Models","created":"2022-12-16","cited_by_count":7,"area":null},{"id":"2303.11131","title":"Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2306.08920","title":"Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2407.04533","title":"Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect","created":"2024-07-05","cited_by_count":7,"area":null},{"id":"2408.05758","title":"VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing","created":"2024-08-11","cited_by_count":7,"area":null},{"id":"2104.02558","title":"Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model","created":"2021-04-06","cited_by_count":6,"area":null},{"id":"2107.06546","title":"ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition","created":"2021-07-14","cited_by_count":6,"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":"2211.06173","title":"Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2510.12851","title":"Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2101.11332","title":"A phonetic model of non-native spoken word processing","created":"2021-01-27","cited_by_count":5,"area":null},{"id":"2102.06816","title":"Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR","created":"2021-02-12","cited_by_count":5,"area":null},{"id":"2106.04897","title":"Unsupervised Automatic Speech Recognition: A Review","created":"2021-06-09","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":"2206.15056","title":"FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition","created":"2022-06-30","cited_by_count":5,"area":null},{"id":"2211.09949","title":"Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers","created":"2022-11-17","cited_by_count":5,"area":null},{"id":"2406.02361","title":"Using Self-supervised Learning Can Improve Model Fairness","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2409.16295","title":"Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget","created":"2024-09-09","cited_by_count":5,"area":null}],"next_cursor":"100"}