Room Acoustics Simulation Using Deep Learning Image Analysis
AssigneeDTS, Inc.
InventorsMartin WALSH, Aoife MCDONAGH, Michael M. GOODWIN, Edward STEIN, Peter CORCORAN
Life of this patent
Estimating the term…
Abstract
A method comprises: receiving an image of a real-world environment; using a machine learning classifier, classifying the image to produce classifications associated with acoustic presets for an acoustic environment simulation, the acoustic presets each including acoustic parameters that represent sound reverberation; and selecting an acoustic preset among the acoustic presets based on the classifications.
Claims25
A method comprising:
- receiving an image of a real-world environment;
- using a machine learning classifier, classifying the image to produce classifications associated with acoustic presets for an acoustic environment simulation, the acoustic presets each including acoustic parameters that represent sound reverberation;
- selecting an acoustic preset among the acoustic presets based on the classifications;
- and
- performing the acoustic environment simulation based on the acoustic parameters of the acoustic preset by modeling sound reverberation for one or more virtual sound objects placed virtually in the real-world environment based on the acoustic parameters of the acoustic preset.
(canceled)
(canceled)
(canceled)
(canceled)
An apparatus comprising:
- a processor configured to:
- receive an image of a real-world environment;
- use a trained machine learning classifier including one or more neural networks to classify the image directly to classifications associated with acoustic presets for an acoustic environment simulation, the acoustic presets each including acoustic parameters that represent sound reverberation;
- select an acoustic preset among the acoustic presets based on the classifications;
- and
- perform the acoustic environment simulation based on the acoustic parameters of the acoustic preset.
A non-transitory computer readable medium encoded with instructions that, when executed by a processor, cause the processor to:
- receive an image of a real-world environment;
- use a machine learning classifier, previously trained on training images of real-world environments labeled with respective ones of acoustic presets, the acoustic presets each including acoustic parameters that represent sound reverberation, to classify the image directly to classifications associated with the acoustic presets for an acoustic environment simulation;
- select an acoustic preset among the acoustic presets based on the classifications;
- and
- perform the acoustic environment simulation based on the acoustic parameters of the acoustic preset.
(canceled)
Dependencies are inferred from the claim text.