1     Version

V2.1

2     Function

Audio Analysis Transform:

  1. Receives Multichannel Audio.
  2. Transforms Multichannel Audio into frequency bands via Fast Fourier Transform (FFT). The operations of the subsequent AIMs are carried out in discrete frequency bands. When such a configuration is used, a 50% overlap between subsequent Audio Blocks must be employed.
  3. Produces Transform Multichannel Audio, a data structure comprising complex valued audio samples in the frequency domain.

3     Reference Architecture

Figure 13 depicts the Reference Architecture of the Audio Analysis Transform AIM.

Figure 13 – The Audio Analysis Transform AIM

4    I/O Data

Table 8 specifies the Input and Output Data of the Audio Analysis Transform AIM.

Table 8 – I/O Data of the Audio Analysis Transform AIM

Input Description
Multichannel Audio The Audio output of the Microphone Array.
Output Description
Transform Multichannel Audio The result of the application of the Fast Fourier Transform to Multichannel Audio.

5    SubAIMs

No SubAIMs.

6     JSON Metadata

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