Stars
percepnet implemented using Keras, still need to be optimized and tuned.
Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
Apache Heron (Incubating) is a realtime, distributed, fault-tolerant stream processing engine from Twitter