Go To MPAI-MMC AI Modules

1     Function 2     Reference Model 3     Input/Output Data
4     SubAIMs 5     JSON Metadata 6     Profiles
7     Reference Software 8     Conformance Texting 9     Performance Assessment

1     Functions

Multimodal Emotion Fusion (MMC-MEF):

Receives Entity’s Emotion (Text) Emotion in Text
Entity’s Emotion (Speech) Emotion in Speech
Entity’s Emotion (Face) Emotion in Face
Produces Entity’s Emotion Emotion

2     Reference Model

Figure 1 depicts the Reference Model of the Multimodal Emotion Fusion (MMC-MEF) AIM.

Figure 1 – The Multimodal Emotion Fusion (MMC-MEF) AIM Reference Model

3    Input/Output Data

Table 1 specifies the Input and Output Data of the Multimodal Emotion Fusion (MMC-MEF) AIM.

Table 1 – I/O Data of the Multimodal Emotion Fusion (MMC-MEF) AIM

Input data From Description
Emotion (Text) PS-Text Interpretation Emotion in Text
Emotion (Speech) PS-Speech Interpretation Emotion in Speech
Emotion (Face) PS-Face Interpretation Emotion in Face
Output data To Description
Input Emotion Downstream AIM The estimated emotion that fuses all inputs

4     SubAIMs

No SubAIMs.

5     JSON Metadata

https://schemas.mpai.community/MMC/V2.3/AIMs/MultimodalEmotionFusion.json

6     Profiles

No Profiles.

7     Reference Software

8     Conformance Testing

Table 2 provides the Conformance Testing Method for Multimodal Emotion Fusion (MMC-MEF)  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 MMC-MEF AIM

Input Emotion (Text) Shall validate against Emotion schema.
Emotion (Speech) Shall validate against Emotion schema.
Emotion (Face) Shall validate against Emotion schema.
Output Input Entity’s Emotion Shall validate against Emotion schema.

Table 3 provides an example of MMC-MEF AIM conformance testing.

Table 3 – An example MMC-MEF AIM conformance testing

Input Data Data Type Input Conformance Testing Data
Emotion (Text) JSON All JSON Emotion (Text) JSON files to be drawn from Emotion JSON Files
Emotion (Speech) JSON All Emotion (Speech) JSON files to be drawn from Emotion JSON Files
Emotion (Visual) JSON All Emotion (Face) JSON files to be drawn from Emotion JSON Files
Output Data Data Type Output Conformance Testing Criteria
Input Emotion JSON All Emotion JSON File shall validate against Emotion Schema

The two attributes emotion_Name and emotion_SetName must be present in the output JSON file of Emotion. The value of either of the two attributes may be null.

9     Performance Assessment

Go To MPAI-MMC AI Modules