Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play

A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond proactively, fostering fluid, dynamic, and emotionally resonant interactions. We introduce Voila, a family of large voice-language foundation models that make a step towards this vision. Voila moves beyond traditional pipeline systems by adopting a new end-to-end architecture that enables full-duplex, low-latency conversations while preserving rich vocal nuances such as tone, rhythm, and emotion. It achieves a response latency of just 195 milliseconds, surpassing the average human response time. Its hierarchical multi-scale Transformer integrates the reasoning capabilities of large language models (LLMs) with powerful acoustic modeling, enabling natural, persona-aware voice generation -- where users can simply write text instructions to define the speaker's identity, tone, and other characteristics. Moreover, Voila supports over one million pre-built voices and efficient customization of new ones from brief audio samples as short as 10 seconds. Beyond spoken dialogue, Voila is designed as a unified model for a wide range of voice-based applications, including automatic speech recognition (ASR), Text-to-Speech (TTS), and, with minimal adaptation, multilingual speech translation. Voila is fully open-sourced to support open research and accelerate progress toward next-generation human-machine interactions.

BeMERC: Behavior-Aware MLLM-based Framework for Multimodal Emotion Recognition in Conversation

Multimodal emotion recognition in conversation (MERC), the task of identifying the emotion label for each utterance in a conversation, is vital for developing empathetic machines. Current MLLM-based MERC studies focus mainly on capturing the speaker's textual or vocal characteristics, but ignore the significance of video-derived behavior information. Different from text and audio inputs, learning videos with rich facial expression, body language and posture, provides emotion trigger signals to the models for more accurate emotion predictions. In this paper, we propose a novel behavior-aware MLLM-based framework (BeMERC) to incorporate speaker's behaviors, including subtle facial micro-expression, body language and posture, into a vanilla MLLM-based MERC model, thereby facilitating the modeling of emotional dynamics during a conversation. Furthermore, BeMERC adopts a two-stage instruction tuning strategy to extend the model to the conversations scenario for end-to-end training of a MERC predictor. Experiments demonstrate that BeMERC achieves superior performance than the state-of-the-art methods on two benchmark datasets, and also provides a detailed discussion on the significance of video-derived behavior information in MERC.

Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion

Multimodal Emotion Recognition in Conversations (MERC) identifies emotional states across text, audio and video, which is essential for intelligent dialogue systems and opinion analysis. Existing methods emphasize heterogeneous modal fusion directly for cross-modal integration, but often suffer from disorientation in multimodal learning due to modal heterogeneity and lack of instructive guidance. In this work, we propose SUMMER, a novel heterogeneous multimodal integration framework leveraging Mixture of Experts with Hierarchical Cross-modal Fusion and Interactive Knowledge Distillation. Key components include a Sparse Dynamic Mixture of Experts (SDMoE) for capturing dynamic token-wise interactions, a Hierarchical Cross-Modal Fusion (HCMF) for effective fusion of heterogeneous modalities, and Interactive Knowledge Distillation (IKD), which uses a pre-trained unimodal teacher to guide multimodal fusion in latent and logit spaces. Experiments on IEMOCAP and MELD show SUMMER outperforms state-of-the-art methods, particularly in recognizing minority and semantically similar emotions.

GatedxLSTM: A Multimodal Affective Computing Approach for Emotion Recognition in Conversations

Affective Computing (AC) is essential for advancing Artificial General Intelligence (AGI), with emotion recognition serving as a key component. However, human emotions are inherently dynamic, influenced not only by an individual's expressions but also by interactions with others, and single-modality approaches often fail to capture their full dynamics. Multimodal Emotion Recognition (MER) leverages multiple signals but traditionally relies on utterance-level analysis, overlooking the dynamic nature of emotions in conversations. Emotion Recognition in Conversation (ERC) addresses this limitation, yet existing methods struggle to align multimodal features and explain why emotions evolve within dialogues. To bridge this gap, we propose GatedxLSTM, a novel speech-text multimodal ERC model that explicitly considers voice and transcripts of both the speaker and their conversational partner(s) to identify the most influential sentences driving emotional shifts. By integrating Contrastive Language-Audio Pretraining (CLAP) for improved cross-modal alignment and employing a gating mechanism to emphasise emotionally impactful utterances, GatedxLSTM enhances both interpretability and performance. Additionally, the Dialogical Emotion Decoder (DED) refines emotion predictions by modelling contextual dependencies. Experiments on the IEMOCAP dataset demonstrate that GatedxLSTM achieves state-of-the-art (SOTA) performance among open-source methods in four-class emotion classification. These results validate its effectiveness for ERC applications and provide an interpretability analysis from a psychological perspective.

A Human Digital Twin Architecture for Knowledge-based Interactions and Context-Aware Conversations

Recent developments in Artificial Intelligence (AI) and Machine Learning (ML) are creating new opportunities for Human-Autonomy Teaming (HAT) in tasks, missions, and continuous coordinated activities. A major challenge is enabling humans to maintain awareness and control over autonomous assets, while also building trust and supporting shared contextual understanding. To address this, we present a real-time Human Digital Twin (HDT) architecture that integrates Large Language Models (LLMs) for knowledge reporting, answering, and recommendation, embodied in a visual interface. The system applies a metacognitive approach to enable personalized, context-aware responses aligned with the human teammate's expectations. The HDT acts as a visually and behaviorally realistic team member, integrated throughout the mission lifecycle, from training to deployment to after-action review. Our architecture includes speech recognition, context processing, AI-driven dialogue, emotion modeling, lip-syncing, and multimodal feedback. We describe the system design, performance metrics, and future development directions for more adaptive and realistic HAT systems.

OmniVox: Zero-Shot Emotion Recognition with Omni-LLMs

The use of omni-LLMs (large language models that accept any modality as input), particularly for multimodal cognitive state tasks involving speech, is understudied. We present OmniVox, the first systematic evaluation of four omni-LLMs on the zero-shot emotion recognition task. We evaluate on two widely used multimodal emotion benchmarks: IEMOCAP and MELD, and find zero-shot omni-LLMs outperform or are competitive with fine-tuned audio models. Alongside our audio-only evaluation, we also evaluate omni-LLMs on text only and text and audio. We present acoustic prompting, an audio-specific prompting strategy for omni-LLMs which focuses on acoustic feature analysis, conversation context analysis, and step-by-step reasoning. We compare our acoustic prompting to minimal prompting and full chain-of-thought prompting techniques. We perform a context window analysis on IEMOCAP and MELD, and find that using context helps, especially on IEMOCAP. We conclude with an error analysis on the generated acoustic reasoning outputs from the omni-LLMs.

Multimodal Emotion Recognition and Sentiment Analysis in Multi-Party Conversation Contexts

Emotion recognition and sentiment analysis are pivotal tasks in speech and language processing, particularly in real-world scenarios involving multi-party, conversational data. This paper presents a multimodal approach to tackle these challenges on a well-known dataset. We propose a system that integrates four key modalities/channels using pre-trained models: RoBERTa for text, Wav2Vec2 for speech, a proposed FacialNet for facial expressions, and a CNN+Transformer architecture trained from scratch for video analysis. Feature embeddings from each modality are concatenated to form a multimodal vector, which is then used to predict emotion and sentiment labels. The multimodal system demonstrates superior performance compared to unimodal approaches, achieving an accuracy of 66.36% for emotion recognition and 72.15% for sentiment analysis.

Heterogeneous bimodal attention fusion for speech emotion recognition

Multi-modal emotion recognition in conversations is a challenging problem due to the complex and complementary interactions between different modalities. Audio and textual cues are particularly important for understanding emotions from a human perspective. Most existing studies focus on exploring interactions between audio and text modalities at the same representation level. However, a critical issue is often overlooked: the heterogeneous modality gap between low-level audio representations and high-level text representations. To address this problem, we propose a novel framework called Heterogeneous Bimodal Attention Fusion (HBAF) for multi-level multi-modal interaction in conversational emotion recognition. The proposed method comprises three key modules: the uni-modal representation module, the multi-modal fusion module, and the inter-modal contrastive learning module. The uni-modal representation module incorporates contextual content into low-level audio representations to bridge the heterogeneous multi-modal gap, enabling more effective fusion. The multi-modal fusion module uses dynamic bimodal attention and a dynamic gating mechanism to filter incorrect cross-modal relationships and fully exploit both intra-modal and inter-modal interactions. Finally, the inter-modal contrastive learning module captures complex absolute and relative interactions between audio and text modalities. Experiments on the MELD and IEMOCAP datasets demonstrate that the proposed HBAF method outperforms existing state-of-the-art baselines.

Modelling Emotions in Face-to-Face Setting: The Interplay of Eye-Tracking, Personality, and Temporal Dynamics

Accurate emotion recognition is pivotal for nuanced and engaging human-computer interactions, yet remains difficult to achieve, especially in dynamic, conversation-like settings. In this study, we showcase how integrating eye-tracking data, temporal dynamics, and personality traits can substantially enhance the detection of both perceived and felt emotions. Seventy-three participants viewed short, speech-containing videos from the CREMA-D dataset, while being recorded for eye-tracking signals (pupil size, fixation patterns), Big Five personality assessments, and self-reported emotional states. Our neural network models combined these diverse inputs including stimulus emotion labels for contextual cues and yielded marked performance gains compared to the state-of-the-art. Specifically, perceived valence predictions reached a macro F1-score of 0.76, and models incorporating personality traits and stimulus information demonstrated significant improvements in felt emotion accuracy. These results highlight the benefit of unifying physiological, individual and contextual factors to address the subjectivity and complexity of emotional expression. Beyond validating the role of user-specific data in capturing subtle internal states, our findings inform the design of future affective computing and human-agent systems, paving the way for more adaptive and cross-individual emotional intelligence in real-world interactions.

MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network

This paper introduces MAVEN (Multi-modal Attention for Valence-Arousal Emotion Network), a novel architecture for dynamic emotion recognition through dimensional modeling of affect. The model uniquely integrates visual, audio, and textual modalities via a bi-directional cross-modal attention mechanism with six distinct attention pathways, enabling comprehensive interactions between all modality pairs. Our proposed approach employs modality-specific encoders to extract rich feature representations from synchronized video frames, audio segments, and transcripts. The architecture's novelty lies in its cross-modal enhancement strategy, where each modality representation is refined through weighted attention from other modalities, followed by self-attention refinement through modality-specific encoders. Rather than directly predicting valence-arousal values, MAVEN predicts emotions in a polar coordinate form, aligning with psychological models of the emotion circumplex. Experimental evaluation on the Aff-Wild2 dataset demonstrates the effectiveness of our approach, with performance measured using Concordance Correlation Coefficient (CCC). The multi-stage architecture demonstrates superior ability to capture the complex, nuanced nature of emotional expressions in conversational videos, advancing the state-of-the-art (SOTA) in continuous emotion recognition in-the-wild. Code can be found at: https://github.com/Vrushank-Ahire/MAVEN_8th_ABAW.