Titlebook: New Era for Robust Speech Recognition; Exploiting Deep Lear Shinji Watanabe,Marc Delcroix,John R. Hershey Book 2017 Springer International

不規(guī)則

保守黨

Robust Features in Deep-Learning-Based Speech Recognitionic models to such variation, robust features have traditionally been used to create an invariant representation of the acoustic space. Most commonly, robust feature-extraction strategies have explored three principal areas: (a) enhancing the speech signal, with a goal of improving the perceptual qua