Geneva, Switzerland – 21st August 2024. MPAI – Moving Picture, Audio and Data Coding by Artificial Intelligence – the international, non-profit, and unaffiliated organisation developing AI-based data coding standards – has concluded its 47th General Assembly (MPAI-47) by approving for publication the Context-based Audio Enhancement (MPAI-CAE) V2.2 standard and the new Data Types, Formats, and Attributes (MPAI-TFA) V1.0 standard for Community Comments. The new versions are released using the new full web-based publication method.
Technical Specification: Context-based Audio Enhancement (MPAI-CAE) V2-2 improves the user experience for different audio-related applications, such as entertainment, restoration, and communication in a variety of different contexts such as in the home, in the office, and in the studio. V2.2 extends the capabilities of several data formats used across MPAI standard.
Technical Specification: Data Types, Formats, and Attributes (MPAI-TFA) V1.0 specifies Qualifiers – a Data Type containing Sub-Types, Formats, and Attributes – associated to “media” Data Types – currently Text, Speech, Audio, and Visual – that facilitate-enable the operation of an AI Module receiving a Data Type instance.
The capabilities of the standards will be presented online on September 24 at 16:00 UTC for MPAI-CAE V2.2 and August 27 at T14:00 UTC for MPAI-TFA). To attend, please register at https://tinyurl.com/2wj8e4bn for MPAI-CAE V2.2 and at https://tinyurl.com/3p8j74st for MPAI-TFA V1.0.
MPAI is continuing its work plan that involves the following activities:
- AI Framework (MPAI-AIF): developing open-source applications based on the AI Framework.
- AI for Health (MPAI-AIH): developing the specification of a system enabling clients to improve models processing health data and federated learning to share the training.
- Context-based Audio Enhancement (CAE-DC): waiting for response to the Audio Six Degrees of Freedom (CAE-6DF).
- Connected Autonomous Vehicle (MPAI-CAV): developing the new MPAI-CAV Technologies (CAV-TEC) part of the standard.
- Compression and Understanding of Industrial Data (MPAI-CUI): developing use cases and functional requirements for MPAI-CUI V2.0 supporting more corporate risks.
- End-to-End Video Coding (MPAI-EEV): video coding using AI-based End-to-End Video coding.
- AI-Enhanced Video Coding (MPAI-EVC): working on a Call for Technologies.
- Governance of the MPAI Ecosystem (MPAI-GME): working on version 2.0 of the Specification.
- Human and Machine Communication (MPAI-HMC): developing reference software.
- Multimodal Conversation (MPAI-MMC): finalising V2.2 and developing Performance Assessment of some important AI Modules.
- MPAI Metaverse Model (MPAI-MMM): developing the new MPAI-MMM Technologies (MMM-TEC) part of the standard.
- Neural Network Watermarking (MPAI-NNW): developing reference software for enhanced applications.
- Object and Scene Description (MPAI-PAF): finalising V1.2 and developing reference software, conformance testing and new areas for digital humans.
- Portable Avatar Format (MPAI-PAF): finalising V1.2 and developing reference software, conformance testing and new areas for digital humans.
- AI Module Profiles (MPAI-PRF): specifying which features an AI Workflow or and AI Module supports.
- Server-based Predictive Multiplayer Gaming (MPAI-SPG): developing technical report on mitigation of data loss and cheating.
- Data Types, Formats, and Attributes (MPAI-TFA): extending he standard to data types used by other MPAI standards.
- XR Venues (MPAI-XRV): developing the standard enabling improved development and execution of Live Theatrical Performances.
Legal entities and representatives of academic departments supporting the MPAI mission and able to contribute to the development of standards for the efficient use of data can become MPAI members.
Please visit the MPAI website, contact the MPAI secretariat for specific information, subscribe to the MPAI Newsletter and follow MPAI on social media: LinkedIn, Twitter, Facebook, Instagram, and YouTube.
