Nokia Technologies Oy (20240284134). Apparatus, Methods and Computer Programs for Obtaining Spatial Metadata simplified abstract
Contents
Apparatus, Methods and Computer Programs for Obtaining Spatial Metadata
Organization Name
Inventor(s)
Juha Tapio Vilkamo of Helsinki (FI)
Mikko Johannes Honkala of Espoo (FI)
Apparatus, Methods and Computer Programs for Obtaining Spatial Metadata - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240284134 titled 'Apparatus, Methods and Computer Programs for Obtaining Spatial Metadata
Simplified Explanation: The patent application discusses using a machine learning model to process microphone signals and obtain spatial metadata for rendering or processing spatial audio.
- Machine learning model used to process microphone signals
- Obtain spatial metadata for spatial audio processing
- Training the model to work with sub-optimal microphone arrays
- Apparatus with circuitry for accessing the model and processing input data
- Associating spatial metadata with microphone signals for signal processing
Key Features and Innovation: - Utilizing machine learning to process microphone signals for spatial metadata - Training the model to work with low-quality microphone arrays - Enabling high-quality spatial metadata extraction from sub-optimal setups - Circuitry for accessing and processing input data for spatial audio rendering - Associating spatial metadata with microphone signals for signal processing
Potential Applications: The technology can be applied in virtual reality, augmented reality, gaming, and immersive audio experiences.
Problems Solved: - Enhancing spatial audio processing with sub-optimal microphone arrays - Enabling high-quality spatial metadata extraction from low-quality setups
Benefits: - Improved spatial audio rendering - Enhanced immersive experiences in virtual reality and gaming - Better processing of spatial audio with limited resources
Commercial Applications: The technology can be used in VR gaming, audio production, spatial audio applications, and entertainment industries.
Questions about Spatial Metadata Processing: 1. How does the machine learning model improve spatial audio processing? 2. What are the potential limitations of using sub-optimal microphone arrays for spatial metadata extraction?
Original Abstract Submitted
examples of the disclosure relate to obtaining spatial metadata for use in rendering, or otherwise processing spatial audio. in examples of the disclosure a machine learning model can be used to process microphone signals, or data obtained from microphone signals, to obtain the spatial metadata. the machine learning model can be trained to enable high quality spatial metadata to be obtained from sub-optimal or low-quality microphone arrays. examples of the disclosure include an apparatus including circuitry for: accessing a trained machine learning model; determining input data for the machine learning model based on two or more microphone signals; enabling using the machine learning model to process the input data to obtain spatial metadata; and associating the obtained spatial metadata with at least one signal based on the two or more microphone signals to enable processing of the at least one signal based on the obtained spatial metadata.
