This repo contains files for speech denoising using convolutional encoder decoder (CED)
The "Noisy speech database for training speech enhancement algorithms and TTS models" (NSDTSEA) is used for training the model, provided by the University of Edinburgh, School of Informatics, Centre for Speech Technology Research (CSTR. https://datashare.is.ed.ac.uk/handle/10283/27 The data augmentation was performed by manually adding recorded random chunk from different noise samples to the clean dataset.
The complete data set prepared for model is available in google drive. https://drive.google.com/open?id=1HB8m2CGdxF--lyrI0xrkfneY9dd71vIQ