Apple Inc. (20240312468). Spatial Audio Upscaling Using Machine Learning simplified abstract

Spatial Audio Upscaling Using Machine Learning

Organization Name

Apple Inc.

Inventor(s)

Ismael H. Nawfal of Redondo Beach CA (US)

Symeon Delikaris Manias of Los Angeles CA (US)

Mehrez Souden of Los Angeles CA (US)

Joshua D. Atkins of Lexington MA (US)

Spatial Audio Upscaling Using Machine Learning - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240312468 titled 'Spatial Audio Upscaling Using Machine Learning

Simplified Explanation: The patent application describes a method to convert first order ambisonics (FOA) audio into a higher order ambisonics (HOA) format using machine learning.

• **Key Features and Innovation:**

   * Processor formats FOA audio signals into audio frames.
   * Machine learning model reformat the audio into desired HOA format.
   * Output audio in HOA format can be rendered in a playback format of choice.

• **Potential Applications:**

   * Virtual reality audio experiences.
   * Immersive audio for gaming.
   * 3D audio production in film and television.

• **Problems Solved:**

   * Simplifies the conversion process from FOA to HOA.
   * Enhances the quality of audio rendering in different formats.

• **Benefits:**

   * Improved audio quality.
   * Streamlined audio conversion process.
   * Enhanced immersive experiences for users.

• **Commercial Applications:**

   * Audio software development.
   * Virtual reality content creation.
   * Gaming industry for realistic audio effects.

• **Prior Art:**

   Research existing patents related to ambisonics audio processing and machine learning in audio technology.

• **Frequently Updated Research:**

   Stay updated on advancements in machine learning algorithms for audio processing and rendering.

Questions about Ambisonics Audio Processing: 1. What are the potential limitations of using machine learning for audio format conversion?

   - Machine learning models may require extensive training data and computational resources to accurately convert audio formats.

2. How does this technology compare to traditional methods of audio format conversion?

   - This technology offers a more efficient and potentially higher quality conversion process compared to traditional methods.

Original Abstract Submitted

a sound scene is represented as first order ambisonics (foa) audio. a processor formats each signal of the foa audio to a stream of audio frames, provides the formatted foa audio to a machine learning model that reformats the formatted foa audio in a target or desired higher order ambisonics (hoa) format, and obtains output audio of the sound scene in the desired hoa format from the machine learning model. the output audio in the desired hoa format may then be rendered according to a playback audio format of choice. other aspects are also described and claimed.