Method and system for generating spatial procedural audio
A method performed by a programmed processor, the method including receiving an input noise signal, generating, using a machine learning model that has an input based on the input noise signal, a mono audio signal that includes a sound and a spatial parameter for the mono audio signal, and generating spatial audio data by spatially encoding the mono audio signal according to the spatial parameter.
1. A method performed by at least one programmed processor, the method comprising:
obtaining a generated noise signal;
generating spatial audio data that comprises a sound of a virtual object for a system using a machine learning (ML) model that has an input based on the generated noise signal; and
spatially rendering the spatial audio data at an output device.
2. The method of claim 1 , wherein the ML model is a Generative Adversarial Network (GAN) model.
3. The method of claim 1 , wherein the system is an extended reality (XR) environment.
4. The method of claim 1 , wherein the system is a video game.
5. The method of claim 1 , wherein the sound comprises at least one of a comfort noise and a soundscape.
6. The method of claim 1 , wherein the sound is a type of sound, wherein the spatial audio data comprises a different sound of the type of sound based on a different generated noise signal as the input of the ML model.
7. The method of claim 1 , wherein the spatial audio data comprises at least one of: multichannel audio in a surround sound multi-channel format, a Higher Order Ambisonics representation of a sound space that includes at least the sound, or binaural audio signals for driving at least one speaker of the output device.
8. The method of claim 1 , wherein the generation of the spatial audio data is performed according to one or more audio signal processing operations only.
9. The method of claim 1 is performed by the at least one programmed processor of an electronic device that comprises the output device.
10. An electronic device comprising:
a processor; and
memory having instructions stored therein which when executed by the processor causes the electronic device to:
obtain a generated noise signal;
generate spatial audio data that comprises a sound of a virtual object for a system using a machine learning (ML) model that has an input based on the generated noise signal; and
transmitting the spatial audio data to an output device for spatial rendering.
11. The electronic device of claim 10 , wherein the ML model is a generative Adversarial Network (GAN) model.
12. The electronic device of claim 10 , wherein the system is at least one of an extended reality (XR) environment and a video game.
13. The electronic device of claim 10 , wherein the sound comprises at least one of a comfort noise and a soundscape.
14. The electronic device of claim 10 , wherein the sound is a type of sound, wherein the spatial audio data comprises a different sound of the type of sound based on a different generated noise signal as the input of the ML model.
15. The electronic device of claim 10 , wherein the generated noise signal includes either white noise or colored noise.
16. The electronic device of claim 10 , wherein the electronic device is separate from the output device.
17. A non-transitory machine-readable medium having instructions which when executed by a processor of an electronic device:
obtain a generated noise signal;
generate spatial audio data that comprises a sound of a virtual object for a system using a machine learning (ML) model that has an input based on the generated noise signal; and
cause the electronic device to transmit the spatial audio data to an output device.
18. The non-transitory machine-readable medium of claim 17 , wherein the ML model is a Generative Adversarial Network (GAN) model.
19. The non-transitory machine-readable medium of claim 17 , wherein the system is one of an extended reality (XR) environment and a video game.
20. The non-transitory machine-readable medium of claim 17 , wherein the sound comprises at least one of a comfort noise and a soundscape.
21. The non-transitory machine-readable medium of claim 17 , wherein the sound is a type of sound, wherein the spatial audio data comprises a different sound of the type of sound based on a different generated noise signal as the input of the ML model.
22. The non-transitory machine-readable medium of claim 17 , wherein the spatial audio data comprises at least one of: multichannel audio in a surround sound multi-channel format, a Higher Order Ambisonics representation of a sound space that includes at least the sound, or binaural audio signals for driving at least one speaker of the output device.