1      Version

V2.1

2     Functions

  1. Receives Damaged Segment, Damaged List, Synthesised Speech.
  2. Produces Synthesised Speech.

3      Reference Model

4      Input/Output Data

Input data Semantics
Damaged Segment An Audio Segment containing only speech (and not containing music or other sounds) which is either damaged in its entirety or contains one or more Damaged Sections specified in the Damaged List.
Damaged List List of Damaged Segments.
Synthesised Speech Speech synthesised by Neural Network Speech Model.
Output data Semantics
Synthesised Speech Speech synthesised by Speech Restoration Assembly

5      SubAIMs

No SubAIMs.

6      JSON Metadata

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