21 citations · 44 across the 20 of their papers we have counts for
9 papers · 1 filter
AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
Huadai Liu, Kaicheng Luo, Wen Wang +4
Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis tha…
STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
Huadai Liu, Wen Wang, Kaicheng Luo +3
Continuous Variational Autoencoders (VAEs) serve as the fundamental continuous tokenizer for modern neural audio generation systems, enabling high-fidelity reconstruction while pro…
ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing
Huadai Liu, Kaicheng Luo, Jialei Wang +4
While end-to-end video-to-audio generation has greatly improved, producing high-fidelity audio that authentically captures the nuances of visual content remains challenging. Like p…
OmniAudio: Generating Spatial Audio from 360-Degree Video
Huadai Liu, Tianyi Luo, Kaicheng Luo +11
Traditional video-to-audio generation techniques primarily focus on perspective video and non-spatial audio, often missing the spatial cues necessary for accurately representing so…
FlashAudio: Rectified Flows for Fast and High-Fidelity Text-to-Audio Generation
Huadai Liu, Jialei Wang, Rongjie Huang +4
Recent advancements in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational deman…
AudioLCM: Text-to-Audio Generation with Latent Consistency Models
Huadai Liu, Rongjie Huang, Yang Liu +5
Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significan…
MEDIC: Zero-shot Music Editing with Disentangled Inversion Control
Huadai Liu, Jialei Wang, Xiangtai Li +6
Text-guided diffusion models revolutionize audio generation by adapting source audio to specific text prompts. However, existing zero-shot audio editing methods such as DDIM invers…
ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer
Huadai Liu, Rongjie Huang, Xuan Lin +5
Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived q…
ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech
Rongjie Huang, Zhou Zhao, Huadai Liu +3
Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinde…