Bwsnet: automatic perceptual assessment of audio signals

HIGHLIGHTS

• What: This paper introduces BWSNet a model that can be trained from raw human judgements obtained through a BestWorst scaling (BWS) experiment. The authors propose a set of cost functions and constraints interpreting trial-wise ordinal relations as distance comparisons in a metric learning task.
• Who: mc7a from the The University of Glasgow has an agreement with IEEE which allows all STMS, CNRS, Sorbonne Université, Paris, France have published the article: BWSNET: automatic perceptual assessment of audio signals, in the Preprint: Arxiv of 21/01/2024
• How: The authors carried out this first . . .
  

   

  

  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.