The Terms used in this standard whose first letter is capital have the meaning defined in Table 1. The general MPAI Terms are defined in Table 2.
Table 1 – Table of terms and definitions
Term | Definition |
Access Copy Files | Set of files providing the information stored in an audio tape recording, including Restored Audio Files, suitable for audio information access, but not for long-term preservation. |
Audio | Digital representation of an analogue audio signal sampled at a frequency between 8-192 kHz with a number of bits/sample between 8 and 32. |
Audio Block | A set of consecutive Audio samples. |
Audio Channel | A sequence of Audio Blocks. |
Audio File | A .wav file [10]. |
Audio Object | Audio source which is in the audible frequency band. |
Audio Scene Geometry | Spatial information for the Audio Objects which are included in an audio scene. |
Audio Segment | An Audio Block with Start Time and an End Time Labels corresponding to the time of the first and last sample of the Audio Segment, respectively. |
Audio-Visual File | A file containing audio and video according to the MP4 File Format [14]. |
Capstan | The capstan is a rotating spindle used to move recording tape through the mechanism of a tape recorder. |
Damaged List | A list of strings of Texts corresponding to the Damaged Segments (if any) requiring replacement with synthetic segments. |
Damaged Section | An Audio Segment which is damaged in its entirety and is contained in a Damaged Segment. |
Damaged Segment | An Audio Segment containing only speech (and not containing music or other sounds) which is either damaged in its entirety or contains one or more Damaged Sections specified in the Damaged List. |
Degree | Strength of a feature, specifically, with respect to Emotion, “High,” “Medium,” or “Low.” |
Editing List | The description of the speed, equalisation and reading backwards corrections occurred during the restoration process. |
Emotion | A Data Type representing the internal status of a human or avatar resulting from their interaction with the context or subsets of it, such as “Angry”, and “Sad”. |
Emotionless Speech | An Audio File containing speech without music and other sounds, and in which little or no identifiable emotion is perceptible by native listeners. |
Irregularity | An event of interest to preservation in Table 27 and Table 28 |
Irregularity File | A JSON file containing information about Irregularities of the ARP inputs. |
Irregularity Image | An image corresponding to an Irregularity. |
JSON | JavaScript object notation [18]. |
Microphone Array Geometry | Description of the position of each microphone comprising the microphone array and specific characteristics such as microphone type, look directions, and the array type. |
Model Utterance | An Audio Segment used as a model or demonstration of the Emotion to be added to Emotionless Speech in order to produce Speech with Emotion. |
Multichannel Audio | A data structure containing at least 2 time-aligned interleaved Audio Channels. |
Multichannel Audio Stream | A data structure containing Audio Objects packaged with Audio Scene Geometry. |
Neural Network Speech Model | A Neural Network Model trained on Speech Segments for Modelling and used to synthesize replacements for the entire Damaged Segment or Damaged Sections within it. |
Passthrough AIM | An AIM with the same input and output data of an AIM without executing the Function of that AIM. E.g., a Noise Cancellation AIM that does not cancel the noise. |
Preservation Audio File | The input Audio File resulting from the digitisation of an audio open-reel tape to be preserved and, in case, restored. |
Preservation Audio-Visual File | The input Audio-Visual File produced by a camera pointed to the playback head of the magnetic tape recorder and the synchronised Audio resulting from the tape digitisation process. |
Preservation Image | A Video frame extracted from Preservation Audio-Visual File. |
Preservation Master Files | Set of files providing the information stored in an audio tape recording without any restoration. As soon as the original analogue recordings is no more accessible, it becomes the new item for long-term preservation. |
Restored Audio Files | Set of Audio Files derived from the Preservation Audio File, where potential speed, equalisation or reading backwards errors that occurred in the digitisation process have been corrected. |
Restored Speech Segment | An Audio Segment in which the entire segment has been replaced by a synthetic speech segment, or in which each Damaged Segment has been replaced by a synthetic speech segment. |
Speech Features | Descriptor representing a variety of information elements incorporated in a Speech Segment, e.g., personal identity, Personal Status, additional factors such as vocal tension, creakiness, whispery quality, etc. |
Speech Segments for Modelling | A set of Audio Files containing speech segments used to train the Neural Network Speech Model. |
Speech With Emotion File | An Audio File containing speech with emotional features. |
Spherical Coordinate System | A coordinate system where the position of a point is specified by three numbers: the radial distance of that point from a fixed origin, its polar angle measured from a fixed zenith direction, and the azimuthal angle of its orthogonal projection on a reference plane. |
Spherical Grid Resolution | The maximum spherical angle between any two neighbouring sampled points on a sphere. |
Text List | List of texts to be converted into speech by the Speech Synthesis for Restoration AIM. |
Time Code | Number of ms from 1970-01-01T00:00:00.000 according to [8]. |
Time Label | A measure of time from a context-dependent zero time expressed as HH:mm:ss.SSS. |
Transform Audio | A frequency representation of Audio. |
Enhanced Transform Audio | Transform Audio whose samples are Enhanced Transform Audio samples. |
Useful Signal | Digital signal resulting from the A/D conversion of the analogue signal recorded in an audio tape. |
The Terms used in this standard whose first letter is capital and are not already included in Table 1 are defined in Table 2.
Table 2 – MPAI-wide Terms
Term | Definition |
Access | Static or slowly changing data that are required by an application such as domain knowledge data, data models, etc. |
AI Framework (AIF) | The environment where AIWs are executed. |
AI Workflow (AIW) | An organised aggregation of AIMs implementing a Use Case receiving AIM-specific Inputs and producing AIM-specific Outputs according to its Function. |
AI Module (AIM) | A processing element receiving AIM-specific Inputs and producing AIM-specific Outputs according to according to its Function. |
Application Standard | An MPAI Standard designed to enable a particular application domain. |
Channel | A connection between an output port of an AIM and an input port of an AIM. The term “connection” is also used as synonymous. |
Communication | The infrastructure that implements message passing between AIMs. |
Composite AIM | An AIM aggregating more than one AIM. |
Component | One of the 7 AIF elements: Access, Communication, Controller, Internal Storage, Global Storage, MPAI Store, and User Agent. |
Composite AIM | An AIM aggregating more than one AIM. |
Conformance | The attribute of an Implementation of being a correct technical Implementation of a Technical Specification. |
Conformance Tester | An entity authorised by MPAI to Test the Conformance of an Implementation. |
Conformance Testing | The normative document specifying the Means to Test the Conformance of an Implementation. |
Conformance Testing Means | Procedures, tools, data sets and/or data set characteristics to Test the Conformance of an Implementation. |
Connection | A channel connecting an output port of an AIM and an input port of an AIM. |
Controller | A Component that manages and controls the AIMs in the AIF, so that they execute in the correct order and at the time when they are needed. |
Data Format | The standard digital representation of data. |
Data Semantics | The meaning of data. |
Ecosystem | The ensemble of the following actors: MPAI, MPAI Store, Implementers, Conformance Testers, Performance Testers and Users of MPAI-AIF Implementations as needed to enable an Interoperability Level. |
Explainability | The ability to trace the output of an Implementation back to the inputs that have produced it. |
Fairness | The attribute of an Implementation whose extent of applicability can be assessed by making the training set and/or network open to testing for bias and unanticipated results. |
Function | The operations effected by an AIW or an AIM on input data. |
Global Storage | A Component to store data shared by AIMs. |
Internal Storage | A Component to store data of the individual AIMs. |
Identifier | A name that uniquely identifies an Implementation. |
Implementation |
|
Implementer | A legal entity implementing MPAI Technical Specifications. |
ImplementerID (IID) | A unique name assigned by the ImplementerID Registration Authority to an Implementer. |
ImplementerID Registration Authority (IIDRA) | The function within the MPAI Store to assign ImplementerID’s to Implementers. |
Interoperability | The ability to functionally replace an AIM with another AIM having the same Interoperability Level. |
Interoperability Level | The attribute of an AIW and its AIMs to be executable in an AIF Implementation and to: |
Knowledge Base | Structured and/or unstructured information made accessible to AIMs via MPAI-specified interfaces. |
Message | A sequence of Records transported by Communication through Channels. |
Normativity | The set of attributes of a technology or a set of technologies specified by the applicable parts of an MPAI standard. |
Performance | The attribute of an Implementation of being Reliable, Robust, Fair and Replicable. |
Performance Assessment | The normative document specifying the procedures, the tools, the data sets and/or the data set characteristics to Assess the Grade of Performance of an Implementation. |
Performance Assessment Means | Procedures, tools, data sets and/or data set characteristics to Assess the Performance of an Implementation. |
Performance Assessor | An entity authorised by MPAI to Assess the Performance of an Implementation in a given Application domain. |
Profile | A particular subset of the technologies used in MPAI-AIF or an AIW of an Application Standard and, where applicable, the classes, other subsets, options and parameters relevant to that subset. |
Record | A data structure with a specified structure. |
Reference Model | The AIMs and theirs Connections in an AIW. |
Reference Software | A technically correct software implementation of a Technical Specification containing source code, or source and compiled code. |
Reliability | The attribute of an Implementation that performs as specified by the Application Standard, profile and version the Implementation refers to, e.g., within the application scope, stated limitations, and for the period of time specified by the Implementer. |
Replicability | The attribute of an Implementation whose Performance, as Assessed by a Performance Assessor, can be replicated, within an agreed level, by another Performance Assessor. |
Robustness | The attribute of an Implementation that copes with data outside of the stated application scope with an estimated degree of confidence. |
Service Provider | An entrepreneur who offers an Implementation as a service (e.g., a recommendation service) to Users. |
Standard | The ensemble of Technical Specification, Reference Software, Conformance Testing and Performance Assessment of an MPAI application Standard. |
Technical Specification | (Framework) the normative specification of the AIF.
(Application) the normative specification of the set of AIWs belonging to an application domain along with the AIMs required to Implement the AIWs that includes:
|
Testing Laboratory | A laboratory accredited by MPAI to Assess the Grade of Performance of Implementations. |
Time Base | The protocol specifying how Components can access timing information. |
Topology | The set of AIM Connections of an AIW. |
Use Case | A particular instance of the Application domain target of an Application Standard. |
User | A user of an Implementation. |
User Agent | The Component interfacing the user with an AIF through the Controller. |
Version | A revision or extension of a Standard or of one of its elements. |
Zero Trust | A model of cybersecurity primarily focused on data and service protection that assumes no implicit trust. |