Loading…
Schedule as of Oct 11, 2022 - subject to change

Default Time Zone is EDT - Eastern Daylight Time


Back To Schedule
Wednesday, October 19 • 3:15pm - 4:45pm
Moving Picture, Audio, and Data Coding by Artificial Intelligence (MPAI) – New Audio Standards Exploiting Artificial Intelligence

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Standards for AI-based data coding – intended to be the transformation of data from one format into another more convenient to an application – has driven the international, not-for-profit, and unaffiliated organization called Moving Picture, Audio, and Data Coding by Artificial Intelligence (MPAI). MPAI develops standards based on a rigorous process that combines open participation in the early phases of standard development, at the time technologies are called for, and at the end of the process, and restricted participation at the time the standard is developed. The MPAI standards work ranges from Server-based Predictive Multiplayer Gaming (MPAI-SPG) to AI-based End-to-End Video Coding (MPAI-EEV), from Connected Autonomous Vehicle (CAV) to injecting watermarking in neural networks (Neural Network Watermarking, MPAI-NNW), and to defining Conformance Testing and IPR framework guidelines.

The proposed workshop intends to present an overview of the MPAI work and, more in detail, the audio-associated standards currently approved: the MPAI AI Framework (AIF) standard which defines the environment, the metadata and the APIs that are called by AI Workflows (AIW) composed of interchangeable AI Modules (AIMs); the MPAI Context-based Audio Enhancement (CAE) standard which focuses on audio applications; and the MPAI Multimodal Conversation (MMC) standard which enables human-machine conversation emultating human-human conversation in completeness and intensity using AI.

Speakers
avatar for Marina Bosi

Marina Bosi

Marina Bosi is a founding Director of the Moving Picture, Audio, and Data Coding by Artificial Intelligence (MPAI) and the Chair of the Context-based Audio Enhancement (MPAI-CAE) Development Group.  Dr. Bosi, currently AES Treasurer, has served the Society as President, VP of the... Read More →
MS

Mark Seligman

Speechmorphing, Inc.
Dr. Mark Seligman is Chief Linguist at Speech Morphing, Inc., a vendor of text-to-speech and speech translation services. Mark is also Founder, President, and CEO of Spoken Translation, Inc. In 1998, he organized the first speech translation system demonstrating broad coverage with... Read More →


Wednesday October 19, 2022 3:15pm - 4:45pm EDT
3D05/08
  Special Event, Workshops Oct 19 & 20