Emotion Recognition in Conversations

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 38

All topics

Multimodal Hidden Markov Models for Persistent Emotional State Tracking
May 13, 2026Anamika Ragu, Aneesh JonelagaddaEmotion Recognition in Conversations Valence-Arousal Modeling
Kaliber AI, San Mateo, California, USA.
Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic Agents
May 8, 2026Deeraj S K, Sadhana Devarajan, Krishna Mehra +1Emotion Recognition in Conversations Adversarial Robustness of Language Models
Department of Artificial Intelligence, Sardar Vallabhbhai National Institute of Technology, Surat, India
Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study
May 4, 2026Patrícia Pereira, Helena Moniz, Joao Paulo CarvalhoPrototype-Based Learning Class-Imbalanced Learning
Instituto Superior Técnico, Av. Rovisco Pais, 1, Lisbon, 1049-001, Portugal. · INESC-ID, Rua Alves Redol, 9, Lisbon, 1000-029, Portugal. · Faculdade de Letras da Universidade de Lisboa, Alameda da Universidade, Lisbon, 1600-214, Portugal.
EmoTransCap: Dataset and Pipeline for Emotion Transition-Aware Speech Captioning in Discourses
Apr 29, 2026Shuhao Xu, Yifan Hu, Jingjing Wu +3Emotion Recognition in Conversations Controllable Speech Generation
Inner Mongolian University, China · State Key Laboratory of Autonomous Intelligent Unmanned Systems, Tongji University
ML-SAN: Multi-Level Speaker-Adaptive Network for Emotion Recognition in Conversations
Apr 28, 2026Kexue Wang, Yinfeng Yu, Liejun WangSpeech Processing Emotion Recognition in Conversations
Joint Research Laboratory for Embodied Intelligence, Xinjiang University · Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University · School of Computer Science and Technology, Xinjiang University, Urumqi 830017, China
Emotion-Cause Pair Extraction in Conversations via Semantic Decoupling and Graph Alignment
Apr 21, 2026Tianxiang Ma, Weijie Feng, Xinyu Wang +1Relation Extraction Emotion Recognition in Conversations
Hefei University of Technology
SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression
Apr 20, 2026Shaowei Zhang, Faqiang Qian, Yan Chen +5RL for Language Models Emotion Recognition in Conversations
1SenseTime · 2Tsinghua University · 3Shanghai Jiao Tong University +1
Exposing Weaknesses in Emotion Recognition in Conversations
Date pendingAmir Ben Khalifa, Fanny Bezancon, Bessam Abdulrazak +1Emotion Recognition in Conversations
Department of Computer Science, Université de Sherbrooke Sherbrooke, Quebec, Canada · Polytech Nantes engineering school, Computer Sciences, Université de Nantes Nantes, France

May 13, 2026, cs.AIJ/K move · Enter open · S save

Multimodal Hidden Markov Models for Persistent Emotional State Tracking

Anamika Ragu, Aneesh Jonelagadda

Kaliber AI, San Mateo, California, USA.

Emotion Recognition in Conversations Valence-Arousal Modeling Multimodal Emotion Recognition Sequence Modeling Affective Computing Hidden Markov Models+1

Open paper AskPDF arXiv

Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understanding and guiding communication in applied, especially clinical, conversational contexts. Existing approaches to emotion recognition operate at the utterance level, obscuring the persistent phases that characterize real conversational dynamics. We propose a lightweight framework that models conversational emotion as a sequence of latent emotional regimes using sticky factorial HDP-HMMs over multimodal valence-arousal representations derived from simultaneous video, audio and textual input. We evaluate the quality of regime prediction using LLM-as-a-Judge, geometric, and temporal consistency metrics, demonstrating that the sticky HDP-HMM produces more interpretable regime sequences than the baseline Gaussian HMM at a fraction of the computational cost of LLM-based dialogue state tracking methods. In addition, Question-Answer experiments in a clinical dataset suggest that meaningful emotional phases can reliably be recovered from multimodal valence-arousal trajectories and used to improve the quality of LLM responses in unstable affective regimes via context augmentation. This framework thus opens a path toward interpretable, lightweight, and actionable analysis of conversational emotion dynamics at scale.

Momentum

Related topics

Latest papers 38