Data augmentation using spectral warping for low resource children asr

HIGHLIGHTS

• who: Hemant Kumar Kathania from the Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland have published the research work: Data Augmentation Using Spectral Warping for Low Resource Children ASR, in the Journal: (JOURNAL)
• what: The authors propose a based data augmentation method to capture more acoustic and speaker variability. Now, in this study the authors investigate the effectiveness of the spectral warping based data augmentation in low resource children ASR.
• how: The authors used the augmented data for system training using different spectral warping parameter ud835udefd on train set and the . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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