1 Version
V2.1
2 Functions
CAE-EAE
- Receives Microphone Array Audio from a Microphone Array recordings
- Extracts
- The speech signals from individual speakers.
- the Spatial Attitudes of the speakers with respect to the position of the Microphone Array to enable the spatial representation of the speech signals by an interested party.
- Reduces the background noise and the reverberation that reduce speech intelligibility.
- Provides the Audio Scene Geometry and the speech signals packaged in a format that is amenable to further processing for efficient delivery and further processing.
3 Reference Model
Figure 1 – Enhanced Audioconference Experience (CAE-EAE) AIW
4 Input/Output Data
Table 1 – Input/Output Data of CAE-EARAIW
Input | Comments |
Microphone Array Geometry | Data Type representing the position of each microphone comprising a Microphone Array and specific characteristics such as microphone type, look directions, and the array type. |
Microphone Array Audio | A Data Type whose structure contains between 4 and 256 time-aligned interleaved Audio Channels organised in blocks. |
Output data | Comments |
Multichannel Audio Stream | Interleaved Multichannel Audio packaged with Time Code as specified in |
5 SubAIMs
The AIMs required by the Speech Restoration System AIW are described in Table 1
Table 11 – AI Modules of of CAE-EAE AIW
AIW | AIMs | Names | JSON |
CAE-EAE | Enhanced Audioconference Experience | X | |
CAE-AAT | Audio Analysis Transform | X | |
CAE-SFD | Sound Field Description | X | |
CAE-SDS | Speech Detection and Separation | X | |
CAE-NCM | Noise Cancellation Module | X | |
CAE-AST | Audio Synthesis Transform | X | |
CAE-ADP | Audio Description Packaging | X |
6 JSON Metadata
https://schemas.mpai.community/CAE/V2.1/AIWs/EnhancedAudioconferenceExperience.json