{"total":19,"rows":[{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2307.07961","title":"EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes","created":"2023-07-16","cited_by_count":82,"area":null},{"id":"2212.09171","title":"Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data","created":"2022-12-18","cited_by_count":21,"area":null},{"id":"2402.06244","title":"Quantifying and Enhancing Multi-modal Robustness with Modality Preference","created":"2024-02-09","cited_by_count":16,"area":null},{"id":"2108.02510","title":"Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation","created":"2021-08-05","cited_by_count":12,"area":null},{"id":"2111.02172","title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","created":"2021-11-03","cited_by_count":11,"area":null},{"id":"2205.08383","title":"Bias and Fairness on Multimodal Emotion Detection Algorithms","created":"2022-05-11","cited_by_count":10,"area":null},{"id":"2202.01072","title":"Interpretability for Multimodal Emotion Recognition using Concept Activation Vectors","created":"2022-02-02","cited_by_count":8,"area":null},{"id":"2203.04443","title":"Estimating the Uncertainty in Emotion Class Labels with Utterance-Specific Dirichlet Priors","created":"2022-03-08","cited_by_count":8,"area":null},{"id":"2202.08974","title":"Multimodal Emotion Recognition using Transfer Learning from Speaker Recognition and BERT-based models","created":"2022-02-16","cited_by_count":7,"area":null},{"id":"2203.16794","title":"MMER: Multimodal Multi-task Learning for Speech Emotion Recognition","created":"2022-03-31","cited_by_count":7,"area":null},{"id":"2601.19956","title":"VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2101.00738","title":"A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition","created":"2021-01-04","cited_by_count":2,"area":null},{"id":"2204.11382","title":"Real-time Speech Emotion Recognition Based on Syllable-Level Feature Extraction","created":"2022-04-25","cited_by_count":2,"area":null},{"id":"2206.02436","title":"Detecting Interlocutor Confusion in Situated Human-Avatar Dialogue: A Pilot Study","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2211.04834","title":"Distribution-based Emotion Recognition in Conversation","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2412.06581","title":"EmoSpeech: A Corpus of Emotionally Rich and Contextually Detailed Speech Annotations","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2412.08683","title":"Emotional Vietnamese Speech-Based Depression Diagnosis Using Dynamic Attention Mechanism","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2509.18175","title":"ERFC: Happy Customers with Emotion Recognition and Forecasting in Conversation in Call Centers","created":"2025-09-17","cited_by_count":0,"area":null}],"next_cursor":null}