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. Function

  1. Receives Irregularity File (Audio) and Audio Files from Audio Analysis for Recording.
  2. Receives Irregularity File (Video) and Irregularity Images from Video Analysis for Recording.
  3. Classifies and selects the relevant Irregularities of the Preservation Audio-Visual File and Preservation Audio File.
  4. Sends the Irregularity File related to the selected Irregularities to Tape Audio Restoration.
  5. Sends the Irregularity Files related to the selected Irregularities and the corresponding Irregularity Images to Packaging for Audio Recording.

2. Reference Model

Figure 1 – Reference Model of Tape Irregularity Classification

3. Input/Output Data

Input data Semantics
Irregularity Audio File Audio Segments corresponding to Irregularities of the Preservation Audio File.
Audio Irregularity File A file containing all Irregularities detected by Audio Analysis for Recording and Audio Analysis for Recording.
Video Irregularity File A file containing all Irregularities detected by Video Analysis for Recording and Audio Analysis for Recording.
Irregularity Images Images corresponding to Irregularities of the Preservation Video File.
Output data Semantics
Irregularity File Irregularity File produced by Tape Irregularity Classifier sent to Tape Audio Restoration.
Irregularity Images Irregularity Images produced by Video Analysis for Recording.

4. SubAIMs

No SubAIMs.

5. JSON Metadata

https://schemas.mpai.community/CAE1/V2.4/data/TapeIrregularityClassification.json

6. Profiles

7. Reference Software

The CAE-TICReference Software can be downloaded from the MPAI Git.

8. Conformance Testing

Receives Irregularity Audio File Shall validate against the Audio Object schema.
The Qualifier shall validate against the Audio Qualifier schema.
The values of any Sub-Type, Format, and Attribute of the Qualifier shall correspond with the Sub-Type, Format, and Attributes of the Audio-Visual Object Qualifier schema.
Audio Irregularity File Shall validate against the Irregularity File schema.
Video Irregularity File Shall validate against the Irregularity File schema.
Irregularity Images Shall validate against the Visual Object schema.
The Qualifier shall validate against the Visual Qualifier schema.
The values of any Sub-Type, Format, and Attribute of the Qualifier shall correspond with the Sub-Type, Format, and Attributes of the Visual Object Qualifier schema.
Produces Irregularity File Shall validate against the Irregularity File schema.
Irregularity Images Shall validate against the Visual Object schema.
The Qualifier shall validate against the Visual Qualifier schema.
The values of any Sub-Type, Format, and Attribute of the Qualifier shall correspond with the Sub-Type, Format, and Attributes of the Visual Object Qualifier schema.

9. Performance Assessment

Table 29 gives the Audio Recording Preservation (ARP) Tape Irregularity Classifier Means and how they are used.

Table 29 – AIM Means and use of Audio Recording Preservation (ARP) Tape Irregularity Classifier.

Means Actions
Performance Assessment Dataset DS1: n Irregularity Files from Audio Analyser.

DS2: n Audio Files related to DS1.

DS3: n Irregularity Files from Video Analyser.

DS4: n Irregularity Images related to DS3.

DS5: n output Irregularity Files in the format of port IrregularityFileOutput_1, containing correctly classified Irregularities.

DS6: n output Irregularity Files in the format of port IrregularityFileOutput_2, containing correctly classified Irregularities.
Procedure 1.     Feed Tape Irregularity Classifier under Assessment with DS1, DS2, DS3 and DS4.

2.     Analyse the Irregularity Files resulting from port IrregularityFileOutput_1.

3.     Analyse the Irregularity Files resulting from port IrregularityFileOutput_2.
Evaluation 1.     Verify the conditions:

a.     The Irregularity Files are syntactically correct and conforming to the JSON schema provided in CAE Technical Specification.

b.     The Irregularity Files resulting from port IrregularityFileOutput_1 contain only Irregularities of interest for the Tape Audio Restoration (i.e., Irregularities with IrregularityType SSV, ESV or SB).

c.     All output Irregularity Images are conforming to the JPEG standard [8].

d.     For each of the n tuples of input records, the output Irregularity Images are equal to the input Irregularity Images corresponding to the Time Labels indicated in the Irregularity Files coming from port IrregularityFileOutput_2.

2.     By inspecting the Irregularity Files resulting from port IrregularityFileOutput_1, for each of the n tuples of input records, compute the values of Recall (R) and Precision (P) for each of the 13 labels of IrregularityType defined in Tables 17 and 18 of [3].

3.     For each label l of IrregularityType, compute the average value of Recall ( ) and Precision ( ) measures obtained at point 2.

4.    Compute the average value of Recall ( ) and Precision ( ) measures obtained at point 3.

5.     Accept the AIM under Assessment if:

a.   R’>0.9

b.   P’>0.9

Figure 12 – Tape Irregularity Classifier.

After the Assessment, Perormance Assessor shall fill out Table 30.

Table 30 – Performance Assessment form of Audio Recording Preservation (ARP) Tape Irregularity Classifier.

Performance Assessor ID Unique Performance Assessor Identifier assigned by MPAI
Standard, Use Case ID and Version Standard ID and Use Case ID, Version and Profile of the standard in the form “CAE-ARP-V2.4”.
Name of AIM Tape Irregularity Classifier
Implementer ID Unique Implementer Identifier assigned by MPAI Store.
AIM Implementation Version Unique Implementation Identifier assigned by Implementer.
Neural Network Version* Unique Neural Network Identifier assigned by Implementer.
Identifier of Performance Assessment Dataset Unique Dataset Identifier assigned by MPAI Store.
Assessment ID Unique Assessment Identifier assigned by Performance Assessor.
Actual output Actual output provided as a matrix of n rows containing  and  values.

Tuple # Label R P
1 SP Measure 1 Measure 1
… … … …
1 SB Measure Measure
… … … …
n SP Measure Measure
… … … …
n SB Measure Measure
Execution time* Duration of Assessment execution.
Assessment comment* –
Assessment Date yyyy/mm/dd.

* Optional field