{"total":185,"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":"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":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"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":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157,"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":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126,"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":"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":"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":"2302.14367","title":"BrainBERT: Self-supervised representation learning for intracranial recordings","created":"2023-02-28","cited_by_count":72,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2406.06371","title":"mHuBERT-147: A Compact Multilingual HuBERT Model","created":"2024-06-10","cited_by_count":66,"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":"2202.03896","title":"Speech Emotion Recognition using Self-Supervised Features","created":"2022-02-07","cited_by_count":53,"area":null},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2101.00387","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","created":"2021-01-02","cited_by_count":52,"area":null},{"id":"2305.10716","title":"A Survey on Time-Series Pre-Trained Models","created":"2023-05-18","cited_by_count":52,"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":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","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":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38,"area":null},{"id":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"area":null},{"id":"2204.03863","title":"Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning","created":"2022-04-08","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":"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":"2210.07353","title":"JOIST: A Joint Speech and Text Streaming Model For ASR","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2210.14648","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2110.07957","title":"Don't speak too fast: The impact of data bias on self-supervised speech models","created":"2021-10-15","cited_by_count":20,"area":null},{"id":"2305.18957","title":"Wave to Syntax: Probing spoken language models for syntax","created":"2023-05-30","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":"2102.07047","title":"Adversarial defense for automatic speaker verification by cascaded self-supervised learning models","created":"2021-02-14","cited_by_count":16,"area":null},{"id":"2104.13083","title":"Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users","created":"2021-04-27","cited_by_count":16,"area":null},{"id":"2105.03070","title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","created":"2021-05-07","cited_by_count":16,"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":"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":"2211.09944","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","created":"2022-11-17","cited_by_count":16,"area":null},{"id":"2406.04997","title":"On the social bias of speech self-supervised models","created":"2024-06-07","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":"2102.00184","title":"Adversarially learning disentangled speech representations for robust multi-factor voice conversion","created":"2021-01-30","cited_by_count":14,"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":"2110.07592","title":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","created":"2021-10-14","cited_by_count":14,"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":"2305.11579","title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment","created":"2023-05-19","cited_by_count":13,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","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":"2201.09165","title":"A Pre-trained Audio-Visual Transformer for Emotion Recognition","created":"2022-01-23","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":"2103.05149","title":"Contrastive Semi-supervised Learning for ASR","created":"2021-03-09","cited_by_count":11,"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":"2203.16965","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","created":"2022-03-31","cited_by_count":11,"area":null},{"id":"2210.02592","title":"CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations","created":"2022-10-05","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":"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":"2203.09129","title":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","created":"2022-03-17","cited_by_count":10,"area":null},{"id":"2203.12813","title":"Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion","created":"2022-03-24","cited_by_count":10,"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":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2109.00181","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","created":"2021-09-01","cited_by_count":9,"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":"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":"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":"2107.08248","title":"Learning De-identified Representations of Prosody from Raw Audio","created":"2021-07-17","cited_by_count":8,"area":null},{"id":"2303.07682","title":"QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis","created":"2023-03-14","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":"2310.11295","title":"CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation","created":"2023-10-17","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":"2111.00865","title":"MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition","created":"2021-10-27","cited_by_count":7,"area":null},{"id":"2205.00222","title":"StorSeismic: A new paradigm in deep learning for seismic processing","created":"2022-04-30","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":"2210.05291","title":"On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding","created":"2022-10-11","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":"2309.09220","title":"Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables","created":"2023-09-17","cited_by_count":7,"area":null},{"id":"2403.09401","title":"Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learning","created":"2024-03-14","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":"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":"2305.11685","title":"Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation","created":"2023-05-19","cited_by_count":6,"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}],"next_cursor":"100"}