1    Function

Audio Source Localisation (CAE-ASL):

Receives Microphone Array Geometry
Transform Multichannel Audio
Detects Audio Objects in the Audio Scene
Determines Audio Objects’ Spatial Attitudes
Produces Audio Spatial Attitudes

2     Reference Architecture

Figure 14 depicts the Reference Architecture of the Audio Source Localisation AIM.

Figure 14 – Audio Source Localisation AIM

3    I/O Data

Table 9 specifies the Input and Output Data of the Audio Source Localisation AIM.

Table 9 – Audio Source Localisation AIM

Input Description
Microphone Array Geometry The spatial arrangement of the microphones.
Transform Multichannel Audio The result of the application of the Fast Fourier Transform to the Multichannel Audio.
Output Description
Audio Spatial Attitudes The Orientations and Directions of Audio Objects.

4    SubAIMs

No SubAIMs.

5. JSON Syntax

https://schemas.mpai.community/CAE/V2.1/AIMs/AudioSceneLocalisation.json

6     Profiles

No Profiles