Speech Enhancement API improves the quality of degraded speech recordings by removing background noise, reducing reverberation, restoring clipped audio, and performing wideband spectral reconstruction
The clean-speech and noise recordings used to train Deep Xi (https://github.com/anicolson/DeepXi). A validation set is also included. Clean speech:The clean-speech recordings are from the test-clean-1
Clean speech: Noise: Note that the clean-speech and noise recordings used for this training set are separate from those used in the following test sets: Deep Xi Test Set (), Test Set from (), and the
