Technical Specification: Context-based Audio Enhancement (MPAI-CAE) V2.2 specifies technologies that improve the user experience for 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. using context information to act on the input audio content, and potentially deliver the processed output via an appropriate protocol. MPAI-CAE specifies four Use Cases and one Composite AIM. The Use Cases are: Emotion Enhanced Speech (EES), Audio Recording Preservation (ARP), Speech Restoration System (SSR), and Enhanced Audioconference Experience (EAE); the Composite AIM is Audio Scene Description (ASD).
Each Use Case normatively defines:
The word normatively implies that an Implementation claiming Conformance to:
- An AIW, shall:
- Have the AIW Function specified in the appropriate Section of Chapter 2.
- Have all its AIMs and their Connections conforming with the AIW Reference Model specified in the appropriate Section of Chapter 2.
- The AIW and AIM input and output data should have the Formats specified in the appropriate Subsection of Section 6.
- An AIM, shall:
- A data Format, the data shall have the Format specified in Section 6.
Users of this Technical Specification should note that:
This version of the MPAI-CAE Technical Specification has been developed by the CAE-DC Development Committee. Future Versions may revise and/or extend the Scope of the Standard.