AES Show 2024 NY

In this workshop, you'll learn how to turn your love for music into a successful business. Acclaimed music producer, Sabrina Seidman aka SEIDS' tutorials have garnered thousands of views online. She’ll talk about how to decide what you want to do, find the right clients, and make products or services they need. You’ll also learn how to get clients and create your own chances to succeed. By the end of the workshop, you'll have the tools to start building a music career that makes you happy and earns you money.

Join the industry experts on this exciting panel to learn more about Wireless Multichannel Audio Systems, the wide scope of approaches that WMAS facilitates, and how the various technologies can help you with multi-channel wireless set ups in challenging RF environments.

MOTIVATION: Generative AI for audio is quickly proliferating in both the commercial and open source software communities, However, there is still no technical consensus on how novel the generated audio data is, and what (if any) characteristics from the training data are commonly replicated. This workshop will explore existing technical approaches for how to detect memorized audio training data, how often it happens, and what characteristics of the audio are memorized. Additionally, we plan to share recent research on how audio similarity algorithms can be used to attribute audio samples produced by a generative model to specific audio samples in the training set.

FORMAT: this will be in the form of a panel discussion with three parts to it (listed below) – the purpose is to inform the AES community about the technical feasibility of detecting memorization and attributing training data in audio generative models, give audio examples of the results, an outlook for future developments, and solicit feedback from the audience.

• Memorization and generalization in deep learning
• Searching for memorized training data in audio generative models
• Training data attribution using audio similarity measures

ADM-OSC is an industry initiative aimed at standardising Object-Based Audio (OBA) positioning data by implementing the Audio Definition Model (ADM) over Open Sound Control (OSC). As immersive audio gains traction across various industries, from music streaming to gaming, and from live sound to broadcasting, the Audio Definition Model (ADM) is becoming a popular standard for metadata. This includes Serial ADM for broadcast and ADM BWF or XML files for studio use.

The ADM-OSC workgroup was formed four years ago to bridge the gap between immersive live and studio ecosystems. It now includes leading developers and manufacturers who aim to facilitate the sharing of audio object metadata across different environments, from studios to broadcasts to live performances.

Since its initial draft implementation, ADM-OSC has been supported by various audio industry tools, including live rendering engines, digital audio workstations (DAWs), controllers, live tracking systems, and media server solutions. It is currently being deployed in both live and studio productions, with increasing interest from technology developers wanting to join and implement this standard.

ADM-OSC 1.0 is now the published specification, aiming to provide a basic interoperability layer between Object Editors and Object Renderers.

This presentation and workshop will take a dive on ADM-OSC and will cover:
- The origins of ADM-OSC
- Presentation of ADM-OSC 1.0 specification
- Use case/application demonstration
- DAW object positional data to external rendering engine (s)
- Controllers’ data to object panner in DAW for automation recording
- Live tracking (actors, artist) positional data to live rendering engine (s)
- Plugin fest 2023 and 2024 report
- Future considerations
- Application-specific subgroups such as broadcast, VR/Gaming, live rendering, show control