<- Scope Go to ToC References ->
Capitalised Terms in MPAI-PRF are defined in Table 1. All MPAI-defined Terms – some of which are used by MPAI-PRF but not defined in Table 1 -are accessible online. Chapters, Sections, and Annexes are Normative unless they are explicitly identified as Informative (as in this Introduction).
A dash “-” preceding a Term in Table 1 indicates the following readings according to the font:
- Normal font: the Term in the table without a dash and preceding the one with a dash should be read before that Term. For example, “Data” and “- Type” means “Avatar Model.”
- Italic font: the Term in the table without a dash and preceding the one with a dash should be read after that Term. For example, “AI Module” and “- Basic” means “Basic AI Module.”
The definition of all MPAI Terms is available
Table 1 – Terms used in this Technical Specification
| Term | Definition |
| AI Module (AIM) | A data processing component performing a Function by processing AIM-specific Input Data and producing AIM-specific Output Data. |
| – Attribute | A type of input Data or an output Data or a functionality, such as the ability to translate. |
| – Basic | An AIM that does not aggregate other AIMs. |
| – Composite | An AIM aggregating more than one AIM. |
| – Profile | The label that uniquely identifies a set of Attributes. |
| – Sub-Attributes | A Characteristic of an Attribute, e.g., media or language. |
| Avatar | An Object rendered to represent a Human of a Machine in a virtual space. |
| – Model | An inanimate Avatar exposing animation interfaces. |
| – Portable | A Data Type including Avatar ID, Time, Visual Environment, Spatial Attitude, Avatar Model, Body Descriptors, Face Descriptors, Language Preference, Speech Coding, Speech Data, Text, and Personal Status. |
| Body | A digital representation of a human body. |
| – Descriptors | A Data Type representing the features of an Entity’s Body. |
| – Object | A Data Type representing the body of an Entity, head included, face excluded. |
| Context | Information surrounding an Entity and providing additional insight into the information the Entity communicates. |
| Data | Information in digital form. |
| – Format | A standard representation of Data. |
| – Type | An instance of Data with a specific Data Format |
| Entity | A human digitally represented as a Digitised Human in a Virtual Environment or a Virtual Human in a Virtual Environment. |
| Face | A digital representation of a human face. |
| – Descriptors | A Data Type representing the motion and conveying information on the Personal Status of the face of a human or an avatar. |
| – Object | A Data Type representing the face of an Entity. |
| Factor | One of Cognitive State, Emotion, and Social Attitude |
| Modality | One of Text, Speech, Face, or Gesture. |
| Object | Data that can be rendered to cause an Experience. |
| – Audio | A Data Type representing an object or a computer-generated Object that can be rendered to and perceived by a human ear. |
| – Audio-Visual | An Object composed of Audio and Visual Objects sharing the same Spatial Attitude. |
| – Instance | The instance of an Audio Object. |
| – Visual | The digital representation of an object captured by an electromagnetic or high-frequency audio signal or computer-generated that can be rendered to and perceived by a human eye. |
| Personal Status | A Data Type representing the ensemble of information internal to a person expressed by 3 Factors (Cognitive State, Emotion, Social Attitude) conveyed by one or more Modalities (Text, Speech, Face, and Gesture). |
| Point of View | The Spatial Attitude of an Entity user looking at an Environment. |
| Scene Descriptors | The digital representation of the features of a scene. |
| – Audio | A Data Type representing the Audio Objects and their spatial arrangement in an Audio Scene. |
| – Audio-Visual | A Data Type representing the Audio-Visual Objects and their spatial arrangement in an Audio-Visual Scene. |
| – Visual | A Data Type representing the Visual Objects and their spatial arrangement in a Visual Scene. |
| Scene Descriptors | The digital representation of the arrangement of a Scene’s Objects. |
| – Audio | A Data Type representing the spatial arrangement of a Scene’s Audio Objects. |
| – Audio-Visual | A Data Type representing the spatial arrangement of a Scene’s Audio, Visual, and Audio-Visual Objects. |
| – Visual | A Data Type representing the spatial arrangement of a Scene’s Visual Objects. |
| Speech | Digital representation of analogue speech sampled at a frequency between 8 kHz and 96 kHz with a number of bits/sample of 8, 16 or 24, and non-linear and linear quantisation or compressed. Data with characteristics of Speech may be synthetically produced. |
| – Descriptors | A Data Type representing information elements incorporated in a Speech Segment, e.g., personal identity, Personal Status, additional factors such as vocal tension, creakiness, whispery quality, etc. |
| – Model | A Neural Network trained to generate utterances with specific Speech Descriptors. |
| – Object | An Object described by Speech Descriptors. |
| Text | A series of characters drawn from a finite alphabet of a Character Set. |
| – Descriptors | A Data Type including the digital representation of the features of Text. |
| – Object | A string of Text. |
| – Recognised | The Text produced by the Automatic Speech Recognition AIM. |
