Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911586625519616 |
|---|---|
| author | Weng, Yuzhe Wang, Haotian Yu, Xinyi Wu, Xiaoyan Xu, Haoran He, Shan Du, Jun |
| author_facet | Weng, Yuzhe Wang, Haotian Yu, Xinyi Wu, Xiaoyan Xu, Haoran He, Shan Du, Jun |
| contents | 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/ . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10367 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels Weng, Yuzhe Wang, Haotian Yu, Xinyi Wu, Xiaoyan Xu, Haoran He, Shan Du, Jun Artificial Intelligence Sound 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/ . |
| title | Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels |
| topic | Artificial Intelligence Sound |
| url | https://arxiv.org/abs/2604.10367 |