| 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
The Speech Personal Status Extraction (MMC-SPE) AIM receives an utterance (input speech) or its Speech Descriptors and produces the Speech Personal Status using the input speech or its descriptors based on the value of input selector:
| Receives | Input Selector | signaling whether a Speech Object or Speech Descriptors are provided. |
| Speech Object | from which the Personal Status should be extracted. | |
| Speech Descriptors | from which the Personal Status should be extracted. SPD are externally computed | |
| Produces | Speech Personal Status. | Entity’s Personal Status. |
2 Reference Model
Figure 1 depicts the Reference Model of the Speech Personal Status Extraction (MMC-SPE) AIM.
Figure 1 – Speech Personal Status Extraction (MMC-SPE) AIM Reference Model
The speech emotion model of the Speech Personal Status Extraction (MMC‑SPE) AIM is data of Access. The Metadata of the AIM declares it in AccessSources (spe-model) by the URI of the archive that holds it, the file of the archive (Member) and the SHA-256 of that file, and states the terms under which it is published, which do not allow commercial use. The runtime that executes the model is part of the Implementation of the AIM.
3 Input/Output Data
Table 1 specifies the Input and Output Data of the Speech Personal Status Extraction (MMC-SPE) AIM.
Table 1 – I/O Data of the Speech Personal Status Extraction (MMC-SPE) AIM
| Input | Description |
| Input Selector | Signals whether a Speech Object or its Speech Descriptors should be used to extracts Speech Personal Status . |
| Speech Object | Speech Object from which the Personal Status should be extracted.. |
| Speech Descriptors | Descriptors from which the Personal Status should be extracted.. |
| Output | Description |
| Speech Personal Status | The computed Speech Personal Status. |
4 SubAIMs
A Speech Personal Status Extraction (MMC-SPE) AIM instance may be implemented as a Composite AIM as specified in Figure 2.
Figure 2 – Reference Model of Speech Personal Status Extraction (MMC-SPE) Composite AIM
5 JSON Metadata
https://schemas.mpai.community/MMC/V2.4/AIMs/SpeechPersonalStatusExtraction.json
6 Profiles
No Profiles
7. Reference Software
8. Conformance Testing
The Conformance Testing Method for the MMC-SPE Basic AIM is provided here. The Conformance Testing Method for the individual Basic AIMs of the MMC-SPE Composite AIM is provided by the individual Basic AIMs.
Table 2 provides the Conformance Testing Method for MMC-SPE AIM.
Note that a schema may contain references to other schemas. In this case, validation of data for the primary schema implies that any data that refers to a secondary schema shall also validate.
Table 2 – Conformance Testing Method for MMC-SPE AIM
| Input | Input Selector | Shall validate against Selector schema. |
| Speech Object | Shall validate against Speech Object schema. Speech Data shall conform with Speech Qualifier. |
|
| Speech Descriptors | Shall validate against Speech Descriptors schema. | |
| Output | Speech Personal Status | Shall validate against Personal Status schema. |
Table 3 provides an example of MMC-SPEAIM conformance testing.
Table 3 – An example MMC-AQM SPE conformance testing
| Input Data | Data Type | Input Conformance Testing Data |
| Speech Object | .wav | All input Speech files to be drawn from Speech files. |
| Output Data | Data Type | Data Format |
| Emotion (Speech) | JSON | All Emotion JSON files shall validate against Emotion Schema. |
emotion_Name and emotion_SetName must be present in the output JSON file of Emotion. The value of either of the two may be null.
