{"total":59,"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":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"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":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"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":"2102.05109","title":"CDPAM: Contrastive learning for perceptual audio similarity","created":"2021-02-09","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":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"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":"2406.03496","title":"Wings: Learning Multimodal LLMs without Text-only Forgetting","created":"2024-06-05","cited_by_count":23,"area":"mllm"},{"id":"2410.11268","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","created":"2024-10-15","cited_by_count":22,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","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":"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":"2106.00573","title":"One4all User Representation for Recommender Systems in E-commerce","created":"2021-05-24","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":"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":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","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":"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":"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":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","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":"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":"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":"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},{"id":"2204.04645","title":"Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data","created":"2022-04-10","cited_by_count":4,"area":null},{"id":"2402.11819","title":"Head-wise Shareable Attention for Large Language Models","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2210.01703","title":"Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining","created":"2022-10-04","cited_by_count":3,"area":null},{"id":"2211.07769","title":"Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech Representations","created":"2022-11-14","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":"2304.11472","title":"A Comparative Study of Pre-trained Speech and Audio Embeddings for Speech Emotion Recognition","created":"2023-04-22","cited_by_count":3,"area":null},{"id":"2305.17394","title":"One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification","created":"2023-05-27","cited_by_count":3,"area":"distill"},{"id":"2211.15837","title":"Survey on Self-Supervised Multimodal Representation Learning and Foundation Models","created":"2022-11-29","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":"2501.12857","title":"HierPromptLM: A Pure PLM-based Framework for Representation Learning on Heterogeneous Text-rich Networks","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2109.13222","title":"Using Pause Information for More Accurate Entity Recognition","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2204.07162","title":"Spatio-Temporal Analysis of Transformer based Architecture for Attention Estimation from EEG","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2303.00510","title":"A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2303.01125","title":"Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2310.04481","title":"Acoustic and linguistic representations for speech continuous emotion recognition in call center conversations","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2405.19426","title":"Deep Learning for Assessment of Oral Reading Fluency","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2411.03085","title":"Speech Separation with Pretrained Frontend to Minimize Domain Mismatch","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2104.10328","title":"Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2105.00812","title":"Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency","created":"2021-04-08","cited_by_count":0,"area":null},{"id":"2204.05488","title":"Overlapping Word Removal is All You Need: Revisiting Data Imbalance in Hope Speech Detection","created":"2022-04-12","cited_by_count":0,"area":null},{"id":"2207.09145","title":"GAFX: A General Audio Feature eXtractor","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2403.00772","title":"Do Weibo platform experts perform better at predicting stock market?","created":"2024-02-12","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":"2412.05770","title":"KITE-DDI: A Knowledge graph Integrated Transformer Model for accurately predicting Drug-Drug Interaction Events from Drug SMILES and Biomedical Knowledge Graph","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2504.02302","title":"Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2508.11598","title":"Representing Speech Through Autoregressive Prediction of Cochlear Tokens","created":"2025-08-15","cited_by_count":0,"area":null}],"next_cursor":null}