XiaoMi Cloud Service for mi.com

Code for the blog "Neural audio codecs: how to get audio into LLMs"

A Python library for acousticians.

A script that automatically backs up all (or a subset of) your Overleaf projects to a local folder, and optionally pushes to Github or a Rhodecode remote. It works.

Ongoing research training transformer models at scale

DeepAFx-ST - Style transfer of audio effects with differentiable signal processing. Please see https://csteinmetz1.github.io/DeepAFx-ST/

A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions (Interspeech 2025)

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

DDSP: Differentiable Digital Signal Processing

A minimum unofficial implementation of the "A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement" (CRN) using PyTorch

Collection of accessible implementations of Generative Adversarial Networks in Keras.

EBU R128 / ITU-R BS.1770 integrated loudness measurement in Python

Companion code of DAFx23 "Differentiable Feedback Delay Network for Colorless Reverberation"

Control adaptive filters with neural networks.

Collection of Python functions for prediction of turbulence-flat plate interaction noise using Amiet's model

Official repository of the paper: Neural-Enhanced Dynamic Range Compression Inversion: A Hybrid Approach for Resoration Audio Dynamics

N/A

SU2 - Ffowcs-Williams & Hawkings Analogy

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

Transformer-Based Cross-Attention for Joint Magnitude-Phase Speech Enhancement

潘多拉，一个让你呼吸顺畅的ChatGPT。Pandora, a ChatGPT client that lets you breathe freely.

A Lightweight Python API for the AES69-2015 Spatially Oriented Format for Acoustics (SOFA) File Format

使用PyQt5封装了小米音箱连接ChatGPT的客户端

类似按键精灵的鼠标键盘录制和自动化操作 模拟点击和键入 | automate mouse clicks and keyboard input