How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
Official implementation of "Separate Anything You Describe"
Tensorflow 2.x implementation of the stacked dual-signal transformation LSTM network (DTLN) for real-time noise suppression. This repository provides the code for training, infering and serving the DTLN model in python. It also provides pretrained models in SavedModel, TF-lite and ONNX format,…
Unofficial PyTorch implementation of Google AI's VoiceFilter system
rnnoise is a real-time speech denoising library that uses a recurrent neural network to suppress background noise from live voice audio. It is implemented as a lightweight C library with a minimal API, designed for easy integration into audio applications that need low-latency noise reduction. The library employs a gated recurrent unit (GRU) architecture and frequency-domain feature extraction to capture temporal dependencies in speech, operating on short audio frames sequentially for streaming use. It also includes a training pipeline that allows users to train custom noise suppression model
The main features of appleholic/source_separation are: Noise reduction.
Projects with overlapping indexed features include: audio-agi/audiosep — Official implementation of "Separate Anything You Describe". breizhn/dtln — Tensorflow 2.x implementation of the stacked dual-signal transformation LSTM network (DTLN) for real-time noise… mindslab-ai/voicefilter — Unofficial PyTorch implementation of Google AI's VoiceFilter system. xiph/rnnoise — rnnoise is a real-time speech denoising library that uses a recurrent neural network to suppress background noise from…