MPAI-OSD V1.5 AIM - Speech Scene Description

Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance

1 Functions

The Speech Scene Description (OSD‑SSD) AIM receives Speech Objects and their Space-Time information as inputs and produces the Descriptors of a Scene composed of Speech Objects and Speech Scenes. The OSD‑SSD AIM may also produce an Alert conveying information on potential anomalies in the input Speech Objects:

Receives	Space-Time	Of the input Objects having the same time base.
	Speech Objects	Individual Speech Objects.
	Scene Descriptors	Scene the Objects belong to.
Integrates	Space-Time and Speech Object	With Scene Descriptors.
Produces	Speech Scene Descriptors	Output of AIM.
	Alert	Signalling potential anomalies in Object.

2 Reference Model

Figure 1 depicts the Reference Model of the Speech Scene Description (OSD‑SSD) AIM.

Speech Scene Description OSD-SSD AIM

Figure 1 – The Speech Scene Description (OSD‑SSD) AIM

3 I/O Data

Table 1 specifies the Input and Output Data of the Speech Scene Description (OSD‑SSD) AIM.

Table 1 – I/O Data of the Speech Scene Description (OSD‑SSD) AIM

Input	Description
Space-Time	Space-Time of input Objects.
Speech Objects	Input Speech Objects.
Scene Descriptors	Input Scene Descriptors.
Output	Description
Speech Scene Descriptors	The output Speech Scene Descriptors.
Alert	Data signalling potential anomalies in Object.

4 SubAIMs

No SubAIMs.

5 JSON Metadata

https://schemas.mpai.community/OSD/V1.5/AIMs/SpeechSceneDescription.json

6 Profiles

No Profiles.

7 Reference Software

Not part of this specification.

8 Conformance Testing

Table 2 provides the Conformance Testing Method for the OSD‑SSD AIM.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present, and conform with the Qualifier, if present.

Table 2 – Conformance Testing Method for the OSD‑SSD AIM

Receives	Space-Time	Shall validate against Space-Time schema.
	Speech Objects	Shall validate against Speech Object schema. Media-specific Data shall conform with their Qualifiers.
	Scene Descriptors	Shall validate against Scene Descriptors schema.
Produces	Speech Scene Descriptors	Shall validate against Speech Scene Descriptors schema.
	Alert	Shall validate against Alert schema.

9 Performance Assessment