This page is being moved to a new, faster, and mobile-friendly application! Access the enhanced and centralized experience now on MyWorkspace.
ITU's 160 anniversary

Connecting the world and beyond

  •  

ITU-T work programme

Home : ITU-T Home : ITU-T Work Programme : F.746.19     
  ITU-T A.5 justification information for referenced document IEEE P3300 in draft F.746.19
1. Clear description of the referenced document:
Name: IEEE P3300
Title: IEEE P3300 (2022): Moving Picture Audio and Data Coding by Artificial Intelligence (MPAI) Technical Specification — Multimodal Conversion v1.2. This specification defines standardized representations and processing methods for multimodal information (speech, text, audio, video, and sensor data) to describe personal status for AI-based human–machine and human–human interaction.
2. Status of approval:
Approved 2022
3. Justification for the specific reference:
The concept of Personal Status and its multimodal representation (covering Cognitive State, Emotion, and Social Attitude across Speech, Face, and Gesture modalities) are directly adopted from IEEE P3300. F.746.19 uses these definitions to describe requirements for emotion and status analysis in hybrid work environments, ensuring interoperability with existing AI frameworks and avoiding redundant terminology.
4. Current information, if any, about IPR issues:
None
5. Other useful information describing the "Quality" of the document:
IEEE P3300 was developed under IEEE-SA’s formal ballot process with open participation, public review, and change control. It is available through IEEE Xplore and the MPAI specification portal, with supporting conformance and reference software repositories.
6. The degree of stability or maturity of the document:
Maturity, widely implemented
7. Relationship with other existing or emerging documents:
IEEE P3300 is part of the MPAI ecosystem alongside IEEE 3301 (AI framework) and IEEE 3302 (Connected Devices). The definitions of multimodal features and personal status used in F.746.19 are consistent with these related standards and complement ITU-T F.746.3 (Intelligent question-answering framework).
8. Any explicit references within that referenced document should also be listed:
IEEE P3300 references the following key documents: (1) IEEE 3301 (AI Framework for MPAI Systems); (2) MPAI CAV (Audio-Visual Scene Description) Specification; (3) ISO/IEC 23005 (MPEG-V – Media Context and Control); and (4) W3C Emotion ML for emotion representation.
9. Qualification of IEEE:
The IEEE was recognized under the provisions of ITU-T Recommendation A.5 on 1 November 1999. Qualifying information is on file with TSB.
10. Other (for any supplementary information):
The MPAI Consortium is now operating under IEEE as the P3300 Working Group. The specification provides a clear and stable mapping between multimodal data features and affective states, serving as the technical basis for emotion and status analysis modules defined in F.746.19. 
Note: This form is based on Recommendation ITU-T A.5