3 citations · 3 across the 6 of their papers we have counts for
7 papers
InkDiffuser: High-Fidelity One-shot Chinese Calligraphy via Differentiable Morphological Optimization
Kunchong Shi, Jing Zhang
Current Chinese calligraphy generation methods suffer from poor stroke rendering and unrealistic ink morphology, resulting in outputs with limited visual fidelity and artistic flui…
Beyond Video-to-SFX: Video to Audio Synthesis with Environmentally Aware Speech
Xinlei Niu, Jianbo Ma, Dylan Harper-Harris +3
The generation of realistic, context-aware audio is important in real-world applications such as video game development. While existing video-to-audio (V2A) methods mainly focus on…
Inter-Diffusion Generation Model of Speakers and Listeners for Effective Communication
Jinhe Huang, Yongkang Cheng, Yuming Hang +4
Full-body gestures play a pivotal role in natural interactions and are crucial for achieving effective communication. Nevertheless, most existing studies primarily focus on the ges…
SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing
Xinlei Niu, Kin Wai Cheuk, Jing Zhang +8
Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing me…
SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion Model
Xinlei Niu, Jing Zhang, Charles Patrick Martin
We present SoundMorpher, an open-world sound morphing method designed to generate perceptually uniform morphing trajectories. Traditional sound morphing techniques typically assume…
SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation
Xinlei Niu, Jing Zhang, Christian Walder +1
We present SoundLoCD, a novel text-to-sound generation framework, which incorporates a LoRA-based conditional discrete contrastive latent diffusion model. Unlike recent large-scale…
HybridVC: Efficient Voice Style Conversion with Text and Audio Prompts
Xinlei Niu, Jing Zhang, Charles Patrick Martin
We introduce HybridVC, a voice conversion (VC) framework built upon a pre-trained conditional variational autoencoder (CVAE) that combines the strengths of a latent model with cont…