# Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels

arXiv: https://arxiv.org/abs/2604.10367 · HTML: https://mlsanity.com/paper/2604.10367/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 49 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation](https://mlsanity.com/paper/2406.08801/) (2024)
- [OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation](https://mlsanity.com/paper/2506.18866/) (2025)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation](https://mlsanity.com/paper/2508.08248/) (2025)
- [Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset](https://mlsanity.com/paper/2506.22554/) (2025)
- [Affective Faces for Goal-Driven Dyadic Communication](https://mlsanity.com/paper/2301.10939/) (2023)
- [SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation](https://mlsanity.com/paper/2507.09862/) (2025)
- [StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars](https://mlsanity.com/paper/2512.22065/) (2025)
- [DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models](https://mlsanity.com/paper/2312.09767/) (2023)
- [ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment](https://mlsanity.com/paper/2506.19398/) (2025)
- [DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation](https://mlsanity.com/paper/2410.13726/) (2024)
- [OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions](https://mlsanity.com/paper/2505.21724/) (2025)
- [TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation](https://mlsanity.com/paper/2512.14938/) (2025)

## Built on by (most cited first, 1 of 1)

- [SingDance: Compositional Zero-Shot Singing-and-Dancing Video Generation with Role-Aware Audio Conditioning](https://mlsanity.com/paper/2608.16220/) (2026)

## Abstract (arXiv)

Audio-driven human video generation has achieved remarkable success in monologue scenarios, largely driven by advancements in powerful video generation foundation models. Moving beyond monologues, authentic human communication is inherently a full-duplex interactive process, requiring virtual agents not only to articulate their own speech but also to react naturally to incoming conversational audio. Most existing methods simply extend conventional audio-driven paradigms to listening scenarios. However, relying on strict frame-to-frame alignment renders the model's response to long-range conversational dynamics rigid, whereas directly introducing global attention catastrophically degrades lip synchronization. Recognizing the unique temporal Scale Discrepancy between talking and listening behaviors, we introduce a multi-head Gaussian kernel to explicitly inject this physical intuition into the model as a progressive temporal inductive bias. Building upon this, we construct a full-duplex interactive virtual agent capable of simultaneously processing dual-stream audio inputs for both talking and listening. Furthermore, we introduce a rigorously cleaned Talking-Listening dataset VoxHear featuring perfectly decoupled speech and background audio tracks. Extensive experiments demonstrate that our approach successfully fuses strong temporal alignment with deep contextual semantics, setting a new state-of-the-art for generating highly natural and responsive full-duplex interactive digital humans. The project page is available at https://warmcongee.github.io/beyond-monologue/ .