{"total":21,"rows":[{"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":"2202.03896","title":"Speech Emotion Recognition using Self-Supervised Features","created":"2022-02-07","cited_by_count":53,"area":null},{"id":"2312.15316","title":"Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue","created":"2023-12-23","cited_by_count":25,"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":"2106.06598","title":"Leveraging Pre-trained Language Model for Speech Sentiment Analysis","created":"2021-06-11","cited_by_count":9,"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":"2108.01132","title":"The Role of Phonetic Units in Speech Emotion Recognition","created":"2021-08-02","cited_by_count":6,"area":null},{"id":"2404.13509","title":"MFHCA: Enhancing Speech Emotion Recognition Via Multi-Spatial Fusion and Hierarchical Cooperative Attention","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2309.04849","title":"Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2311.07093","title":"A Comprehensive Study on the Effectiveness of ASR Representations for Noise-Robust Speech Emotion Recognition","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2304.00173","title":"Lego-Features: Exporting modular encoder features for streaming and deliberation ASR","created":"2023-03-31","cited_by_count":3,"area":null},{"id":"2203.17023","title":"CTA-RNN: Channel and Temporal-wise Attention RNN Leveraging Pre-trained ASR Embeddings for Speech Emotion Recognition","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2505.07731","title":"Spoken Language Understanding on Unseen Tasks With In-Context Learning","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2109.06112","title":"Beyond Isolated Utterances: Conversational Emotion Recognition","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2510.13906","title":"Switchboard-Affect: Emotion Perception Labels from Conversational Speech","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2109.07228","title":"Dialog speech sentiment classification for imbalanced datasets","created":"2021-09-15","cited_by_count":0,"area":null},{"id":"2301.00964","title":"e-Inu: Simulating A Quadruped Robot With Emotional Sentience","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2308.03150","title":"\"We care\": Improving Code Mixed Speech Emotion Recognition in Customer-Care Conversations","created":"2023-08-06","cited_by_count":0,"area":null},{"id":"2507.12951","title":"UniSLU: Unified Spoken Language Understanding from Heterogeneous Cross-Task Datasets","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2507.19356","title":"Enhancing Speech Emotion Recognition Leveraging Aligning Timestamps of ASR Transcripts and Speaker Diarization","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.20796","title":"Speech Emotion Recognition via Entropy-Aware Score Selection","created":"2025-08-28","cited_by_count":0,"area":null}],"next_cursor":null}