drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
Built on WaveNet's dilated causal convolutions, this implementation uses Keras and Theano to perform real-time speech denoising across variable noise conditions and SNR levels. The architecture supports speaker conditioning and enables inference speedup by processing longer audio segments in single forward passes without recomputing overlapping receptive fields. Pre-trained weights are provided alongside configurable training pipelines for the NSDTSEA dataset.
708 stars. No commits in the last 6 months.
Stars
708
Forks
163
Language
Python
License
MIT
Category
Last pushed
Jul 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/drethage/speech-denoising-wavenet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz...
crlandsc/torch-log-wmse
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful...
KyungsuKim42/tokensynth
The official implementation of TokenSynth (ICASSP 2025)
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.