Context-based Audio Enhancement (MPAI-CAE)

Context-based Audio Enhancement (MPAI-CAE) is an MPAI standard that improves the user experience for several audio-related applications including entertainment, communication, teleconferencing, gaming, post-production, restoration etc. in a variety of contexts such as in the home, in the car, on-the-go, in the studio, etc.

MPAI has developed MPAI-CAE V2 containing the data formats required by the Audio Scene Description Composite AIM. This AIM receives an audio stream from a microphone array and produces a description of the orientation of the composing speech streams.

Technical Specification – Context based Audio Enhancement (MPAI-CAE) WD1.5  is posted with a request for Community Comments. Comments should be  sent to until the 20th of March 2023.

MPAI is indebted to the following individuals for the development of MPAI-CAE Technical Specification V1:

Yan Abu Arab (Speech Morphing Inc.), Marina Bosi (Stanford University), Sergio Canazza (Audio Innova), Mert Burkay Çöteli (ASELSAN A.Ş.), Nadir Dalla Pozza (Audio Innova), Michelangelo Guarise (Volumio), Hüseyin Hacıhabiboğlu (METU), Niccolo’ Pretto (Audio Innova), Paolo Ribeca (James Hutton, Ltd.), Mark Seligman (Speech Morphing Inc.), and Fathy Yassa (Speech Morphing Inc.).

The Institute of Electrical and Electronic Engineers (IEEE) has adopted MPAI-CAE with the name IEEE 3302-2022.

See the public MPAI-CAE documents:

  1. Call for Patent Pool Administrator (closed)
  2. Introduction to MPAI-CAE
  3. MPAI-CAE Standard (V1.4)
  4. About MPAI-CAE
  5.  Call for Technologies (closed)
  6. Framework Licence
  7. Use Cases and Functional Requirements (V1)
  8. Application Note

Visit the About MPAI-CAE page.