1. Functions
Audio Segmentation (MMC-AUS):
| Receives | Speech Object as File |
| Identifies | Speech Time |
| Extracts | Target Speech Object |
| Detects | Speech Overlap |
| Produces | Speech Time |
| Speech Overlap | |
| Speech Object |
2. Reference Architecture
Figure 1 depicts the Reference Architecture of the Audio Segmentation AIM.
Figure 1 – Reference Model of Audio Segmentation AIM
3. I/O Data
Table 1 specifies the Input and Output Data of the Audio Segmentation AIM.
Table 1 – I/O Data of the Audio Segmentation AIM
| Input | Description |
| Speech File | Input Speech file |
| Output | Description |
| Speaker Time | Time Speaker starts speaking |
| Speech Overlap | Number of speakers |
| Speech Object | Speaker’s Speech Object |
4. SubAIMs
No SubAIMs
5. JSON Metadata
https://schemas.mpai.community/MMC/V2.2/AIMs/AudioSegmentation.json
6. Profiles
No Profiles
