Figure 1
From: Restoring speech intelligibility for hearing aid users with deep learning
Training pipeline of the denoising system using a mean opinion score (MOS)-estimator-guided neural architecture search. The denoising network is trained to predict denoised outputs from mixed speech and noise input STFTs. To optimize the remaining error for human acoustic perception, the denoising network architecture and hyperparameters are selected by an evolutionary neural architecture search27,28,29,30. This search is guided by an MOS estimator, which is a deep neural network trained on a dataset generated from around 100,000 human rated audio files.
