A Preliminary Study of Robust Speech Feature Extraction Based on Maximizing the Probability of States in Deep Acoustic Models

HIGHLIGHTS

  • who: Li-Chia Chang and Jeih-Weih Hung from the Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan have published the paper: A Preliminary Study of Robust Speech Feature Extraction Based on Maximizing the Probability of States in Deep Acoustic Models, in the Journal: (JOURNAL)
  • what: This study proposes a novel robust speech feature extraction technique to improve speech recognition performance in noisy environments. The authors provide a little more discussion about the issue that using mean squared error (MSE) as the loss function in most deep-learning-based SE algorithms does not . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?