1     Definition 2     Functional Requirements 3     Syntax
4     Semantics 5    Conformance Testing 6     Performance Assessment

1      Definition

A Data Type describing a Speech Scene’s Speech Objects and Qualifiers, the Speech Scene Descriptors, and their spatial arrangement .

2      Functional Requirements

Speech Scene Descriptors include Scenes in addition to Objects.

3      Syntax

https://schemas.mpai.community/MMC/V2.3/data/SpeechSceneDescriptors.json

4      Semantics

Label Size Description
Header N1 Bytes Speech Scene Descriptors Header
– Standard-SpeechSceneDescriptors 9 Bytes The characters “MMC-SSD-V”
– Version N2 Bytes Major version – 1 or 2 characters
– Dot-separator 1 Byte The character “.”
– Subversion N3 Bytes Minor version – 1 or 2 characters
MInstanceID N4 Bytes Identifier of M-Instance.
SpeechSceneDescriptorsID N5 Bytes Identifier of the Speech Basic Scene.
SpeechSceneSpaceTime N7 Bytes Data about the Speech Scene’s Space-Time.
SpeechObjectCount N6 Bytes Number of Objects in Scene.
SpeechSceneObjectDescriptorsData[] N8 Bytes Data of Speech Scene Objects.
– SpeechObjectSpaceTime N9 Bytes Space-Time info of Speech Object.
– SpeechObjectData N10 Bytes  Speech Object Data.
SpeechSubSceneCount N6 Bytes Number of Sub-Scenes in Scene.
SpeechSceneSubSceneDescriptorsData[] N8 Bytes Data of Speech Scene Sub-Scenes.
– SpeechSubSceneSpaceTime N9 Bytes Space-Time info of Speech Sub-Scenes.
– SpeechSubSceneData N10 Bytes  Speech Sub-Scene Data.
DescrMetadata N11 Bytes Descriptive Metadata.

5     Conformance Testing

A Data instance Conforms with MPAI-MMC V2.3 Speech Scene Descriptors (MMC-SSD) if:

  1. The Data validates against the Speech Scene Descriptors’ JSON Schema.
  2. All Data in the  Speech Scene Descriptors’ JSON Schema
    1. Have the specified type
    2. Validate against their JSON Schemas
    3. Conform with their Data Qualifiers if present.

6     Performance Assessment