{"total":40,"rows":[{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205,"area":null},{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"area":null},{"id":"2406.07162","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","created":"2024-06-11","cited_by_count":40,"area":null},{"id":"2211.05705","title":"DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis","created":"2022-11-10","cited_by_count":27,"area":null},{"id":"2403.01222","title":"Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions","created":"2024-03-02","cited_by_count":27,"area":null},{"id":"2205.14727","title":"CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI","created":"2022-05-29","cited_by_count":26,"area":null},{"id":"2308.11578","title":"Refashioning Emotion Recognition Modelling: The Advent of Generalised Large Models","created":"2023-08-21","cited_by_count":16,"area":null},{"id":"2406.08068","title":"Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey","created":"2024-06-12","cited_by_count":16,"area":null},{"id":"2407.21491","title":"Generative Expressive Conversational Speech Synthesis","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2407.02751","title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","created":"2024-07-03","cited_by_count":15,"area":null},{"id":"2408.09481","title":"PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2024-08-18","cited_by_count":13,"area":null},{"id":"2409.07388","title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2501.13306","title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2312.10201","title":"CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition","created":"2023-12-15","cited_by_count":12,"area":null},{"id":"2405.13049","title":"SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversations","created":"2024-05-19","cited_by_count":12,"area":null},{"id":"2505.20511","title":"Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2405.15708","title":"EmpathicStories++: A Multimodal Dataset for Empathy towards Personal Experiences","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2408.05926","title":"BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2301.05880","title":"TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World","created":"2023-01-14","cited_by_count":7,"area":null},{"id":"2410.09524","title":"Emphasis Rendering for Conversational Text-to-Speech with Multi-modal Multi-scale Context Modeling","created":"2024-10-12","cited_by_count":6,"area":null},{"id":"2502.10973","title":"Akan Cinematic Emotions (ACE): A Multimodal Multi-party Dataset for Emotion Recognition in Movie Dialogues","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2509.22220","title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2412.15622","title":"TouchASP: Elastic Automatic Speech Perception that Everyone Can Touch","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2508.18740","title":"M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2502.13954","title":"Latent Distribution Decoupling: A Probabilistic Framework for Uncertainty-Aware Multimodal Emotion Recognition","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2603.08936","title":"VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2312.09038","title":"Object Recognition from Scientific Document based on Compartment Refinement Framework","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2411.10018","title":"Once More, With Feeling: Measuring Emotion of Acting Performances in Contemporary American Film","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2607.27895","title":"MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2403.04789","title":"TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2410.14145","title":"CAPE: A Chinese Dataset for Appraisal-based Emotional Generation using Large Language Models","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2502.10435","title":"RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2508.01644","title":"DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognition","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2512.19379","title":"OmniMER: Auxiliary-Enhanced LLM Adaptation for Indonesian Multimodal Emotion Recognition","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2603.03327","title":"A benchmark for joint dialogue satisfaction, emotion recognition, and emotion state transition prediction","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.18159","title":"FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.04591","title":"Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.18109","title":"SpEmoC: A Balanced Speaker-Segment Multimodal Emotion Benchmark","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.24430","title":"Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.26726","title":"AtmosERC: Modeling Dialogue-Level Affective Atmosphere for Emotion Recognition in Conversation","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}