Deep learning-based non-intrusive multi-objective speech assessment model with cross-domain features

HIGHLIGHTS

• who: Ryandhimas E. Zezario et al. from the Shenzhen Sustainable Support Program for High-level University under Grant have published the research work: Deep Learning-Based Non-Intrusive Multi-Objective Speech Assessment Model With Cross-Domain Features, in the Journal: (JOURNAL) of 16/Nov/2021
• what: -This study proposes a cross-domain multi-objective speech assessment model called MOSA-Net which can simultaneously estimate the speech quality intelligibility and distortion assessment scores of an input speech signal. By contrast, the intelligibility score refers to the ratio of the number of accurately recognized words/phonemes/sentences . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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