A Perceptually Inspired Data Augmentation Method for Noise Robust CNN Acoustic Models
A Perceptually Inspired Data Augmentation Method for Noise Robust CNN Acoustic Models
L. Tóth,György Kovács,Dirk Van Compernolle
2018 · DOI: 10.1007/978-3-319-99579-3_71
International Conference on Speech and Computer · 20 Citations
TLDR
A data augmentation method that improves the robustness of convolutional neural network-based speech recognizers to additive noise by introducing two simple heuristics that select the less reliable components of the spectrum of the speech signal as candidates for dropout.