Non-intrusive deep learning-based computational speech metrics with high-accuracy across a wide range of acoustic scenes

HIGHLIGHTS

• who: Peter Udo Diehl and colleagues from the Head and Neck Surgery, Campus Benjamin Franklin, Berlin, Germany Editor:, Sejong University have published the research: Non-intrusive deep learning-based computational speech metrics with high-accuracy across a wide range of acoustic scenes, in the Journal: PLOS ONE of 18/08/2022
• what: Improving speech understanding, especially in noisy settings, is the main goal of hearing aids and cochlear implants. To better understand metric differences and failure cases, the authors show scatterplots of the overall category in selected datasets and processing methods (Fig 4A with normalization . . .
  

   

  

  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.