<-References v2.2 <-References v2.3 Go to ToC V2.2 Go to ToC V2.3 AI Modules v2.2-> AI Modules v2.3->
Technical Specification: Context-based Audio Enhancement (CAE-USC) V2.2 specifies the following AI Workflows:
Emotion-Enhanced Speech | Audio Recording Preservation | Speech Restoration System | Enhanced Audioconference Experience |
Note: The specification of Audio Recording Preservation and Enhanced Videoconference Experience is unchanged from V2.1.
Each AI Workflow includes the specification of:
- Functions of the AI Workflow
- Reference Model of the AI Workflow
- I/O data of the AI Workflow
- Functions of AI Modules
- I/O data of the AI Modules
- AIW, AIMs, and JSON Metadata
Each AIW, AIM, and Data Type is specified by individual web pages that can be referenced by other Technical Specifications. The list of links to all AIWs, AIMs, and Data Types is available.
<-References v2.2 <-References v2.3 Go to ToC V2.2 Go to ToC V2.3 AI Modules v2.2-> AI Modules v2.3->