arXiv:2609.18632v1 Announce Type: new Abstract: Multi-modal talking avatar synthesis aims to generate realistic talking videos from a reference portrait and speech. Despite rapid progress in diffusio...
arXiv:2606. 28568v1 Announce Type: cross Abstract: Speech-driven 3D facial animation methods face significant challenges in simultaneously achieving high-fidelity motion and precise artistic control at production quality.
Emo-LiveSync is a real‑time universal lip‑sync video generation framework that builds on LivePortrait and a warp‑based portrait animation model. By aligning audio signals to an implicit motion space through knowledge distillation from a pre‑trained video‑to‑motion model, it achieves high visual fidelity and lip‑sync accuracy while remaining computationally efficient. The method also introduces an expressive control gate for explicit emotion manipulation, enabling content enrichment and generalization to stylized characters beyond photo‑realistic humans.
arXiv:2609.22913v1 Announce Type: cross Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live...
arXiv:2608. 05218v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables fast, photorealistic talking-head rendering, yet accurate lip articulation remains elusive: mouth motion is often over-smoothed and may violate hard articulatory constraints such as bilabial closures, producing the notorious ``leaky mouth'' artifact.
arXiv:2610.19290v1 Announce Type: new Abstract: We present Kandinsky S2V 1.0, an open family of speech-to-video models for controllable audio-driven human animation, comprising Kandinsky S2V 1.0 Lite...
Audio-driven talking head synthesis has achieved impressive progress in lip synchronization and visual quality, yet generating expressive emotional avatars with controllable intensity remains challenging, especially under real-time constraints. In this paper, we present GaussianEmoTalker, an audio-driven framework for real-time emotional talking head synthesis based on 3D Gaussian Splatting.
arXiv:2608. 11590v1 Announce Type: cross Abstract: Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing.
The paper introduces MOCO, a diffusion-based framework that generates 3D avatar motions from concurrent multimodal inputs such as speech audio, text descriptions, and trajectory data. MOCO decouples motion generation by independently producing modality-specific motions at each denoising step and then assembling them according to spatial rules, iteratively refining the combined motion. This approach yields coherent, lifelike, and synchronized movements, outperforming existing baselines on a multimodal benchmark.
ECHO-G is a framework for generating full‑body co‑speech motion for humanoid robots, jointly conditioned on speech audio and timed transcripts. Its Speech‑Grounded Diffusion Transformer (SGDiT) fuses frame‑aligned acoustic features with token‑level linguistic context, preserving distinct granularities while modeling one‑to‑many utterance‑motion relationships directly in robot space. The authors introduce a BEAT2‑derived audio‑text‑robot dataset, a benchmark for co‑speech characteristics, robot‑motion quality, and runtime efficiency, and demonstrate that direct robot‑space generation outperforms human‑motion generation and retargeting pipelines, with joint audio‑text conditioning yielding superior results in both quantitative evaluation and a video‑rating study. "whyItMatters":"The study provides a new dataset, benchmark, and a demonstrably effective method for generating realistic co‑speech motion directly in robot space, advancing practical humanoid robot interaction."
The paper introduces a geometric measure of coarticulation for speech‑driven 3D facial animation, comparing lip‑path length to the shortest route through vowel, consonant, and vowel positions. Using only forced alignment, the measure evaluates four state‑of‑the‑art animation methods, revealing that all produce flatter lip trajectories than captured speech and that some methods lose 15–60% of the fast articulatory component. A pre‑registered viewer study confirms that damping real motion lowers perceived quality while exaggeration is not penalized, and viewers prefer real speech in 73.4% of sentence comparisons.
arXiv:2606. 01031v1 Announce Type: cross Abstract: Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos.