Deep complex convolution recurrent network (DCCRN), which extends CRN with complex structure, has achieved superior performance in MOS evaluation in Interspeech 2020 deep noise suppression challenge (DNS2020).
In this challenge, we open source a sizable speech, keyword, echo and noise corpus for promoting data-driven methods, particularly deep-learning approaches on KWS and SSL.
Sound Audio and Speech Processing
Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality.
Ranked #3 on Speech Enhancement on Deep Noise Suppression (DNS) Challenge (PESQ-NB metric)
Speech Enhancement Audio and Speech Processing Sound