Ge Zhu (朱舸)

Cacophony. Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986

GenerativeSourceSeparation. Open source code for the paper 'Music Source Separation with Generative Flow'

Y-vector. Y-vector: Multiscale Waveform Encoder for Speaker Embedding

Manifold-Constrained-Gradient-ipynb. Unofficial implementation for the paper 'Improving Diffusion Models for Inverse Problems using Manifold Constraints'[https://arxiv.org/abs/2206.00941]

AudioDiffuser. Companion codebase for the paper "A Review on Score-based Generative Models for Audio Applications" (https://arxiv.org/abs/2506.08457)

PodcastFillers_Utils. Utility functions for preprocessing PodcastFillers dataset

Filler-semi-CRF. Codebase for "Transcription free filler word detection with Neural semi-CRFs" [ICASSP2023]

TDspkr-mismatch-study. Code base for "A study of the robustness of raw waveform based speaker embeddings under mismatched conditions"