Free Information Center
MetricGAN+ is an advanced framework for speech enhancement that leverages metric learning and generative adversarial networks to optimize speech quality metrics directly. It improves upon its predecessor, MetricGAN, by enhancing performance and stability in denoising and speech enhancement tasks.
DEMUCS is a deep learning model designed for music source separation with a focus on denoising, enabling the extraction of individual instrument and vocal tracks from mixed audio recordings. It uses convolutional and recurrent neural network architectures to achieve high-quality separation and noise reduction.
OpenUnmix is an open-source tool for music source separation designed to isolate individual audio components such as vocals and instruments from mixed audio tracks. It employs deep learning techniques to perform this task, making it a notable contribution to audio signal processing and music information retrieval.
DeepFilterNet is a deep learning-based speech enhancement method designed to improve audio quality by reducing noise and reverberation in real-time applications. It utilizes a neural network architecture to predict complex spectral filters that enhance speech signals, making it suitable for use in communication devices and hearing aids.