IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Generative models for conditional audio generation

Audiogen Codec

Perceptual Quality Estimator for speech and audio

Versatile audio super resolution (any -> 48kHz) with AudioSR.

Shortcut flow matching Pytorch implementation

The official Implementation of PeriodWave and PeriodWave-Turbo

Unified automatic quality assessment for speech, music, and sound.

easy-to-use implementation of the ISMIR 2013 Audio Degradation Toolbox

🎛 🔊 A Python library for audio.

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

编译原理习题精选 陈意云 PDF

Janus-Series: Unified Multimodal Understanding and Generation Models

📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.

Music repair method to convert lossy MP3 compressed music to lossless music.

[ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"

[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

Official PyTorch implementation of BigVGAN (ICLR 2023)

Official implementation of "AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space models", presented in LAMIR 2024 Workshop

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

🔥🔥🔥A curated list of papers on recent diffusion-based high-resolution image and video synthesis works.