Acoustic characterization based on sensor profiling
View Patent ↗A system, method, and computer-readable medium for an audio processing system which compensates for environment parameters to enhance audio inputs and outputs of an information handling system. More specifically, in certain embodiments, the audio processing system accounts for environmental characteristics including some or all of shape, size, materials, occupant, quantity, location and occlusions.
1. A computer-implementable method for acoustic characterization, comprising:
obtaining information regarding a scene from a sensor, the information regarding the scene comprising visual information regarding the scene;
providing the information regarding the scene to an audio processing system; and,
enhancing audio inputs and outputs based upon the information regarding the scene, the enhancing compensating for environment characteristics deduced from the visual information regarding the scene; and wherein
the sensor comprises a camera; and,
the camera comprises front and rear facing cameras, the front facing camera provides a primary input, the primary input providing the information regarding the scene via front facing camera visual information and the rear-facing camera providing additional information to complete the scene, the additional information to complete the scene comprising rear-facing camera visual information, the audio processing system using the front facing camera visual information and rear-facing camera visual information to identify objects located within the scene and the to identify environmental parameters related to the scene, the environmental parameters comprising location parameters, the audio processing system using the front facing camera visual information and the rear-facing camera visual information to characterize room and environment acoustics and noise sources, the audio processing system performing echo cancellation and noise suppression operations to compensate for the identified objects and environmental parameters.
2. The method of claim 1 , wherein:
the environmental characteristics comprise at least one of shape, size, materials, occupant, quantity, location and occlusions.
3. The method of claim 1 , wherein:
the audio processing system performs at least one of beam forming operations, speech input processing operations and de-reverberation operations based upon the information regarding the scene.
4. A system comprising:
a processor;
a data bus coupled to the processor;
a sensor coupled to the data bus; and
a non-transitory, computer-readable storage medium storing an audio processing system embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for: obtaining information regarding a scene from a sensor, the information regarding the scene comprising visual information regarding the scene;
providing the information regarding the scene to an audio processing system; and,
enhancing audio inputs and outputs based upon the information regarding the scene, the enhancing compensating for environment characteristics deduced from the visual information regarding the scene; and wherein
the sensor comprises a camera; and,
the camera comprises front and rear facing cameras, the front facing camera provides a primary input, the primary input providing the information regarding the scene via front facing camera visual information and the rear-facing camera providing additional information to complete the scene, the additional information to complete the scene comprising rear-facing camera visual information, the audio processing system using the front facing camera visual information and rear-facing camera visual information to identify objects located within the scene and the to identify environmental parameters related to the scene, the environmental parameters comprising location parameters, the audio processing system using the front facing camera visual information and the rear-facing camera visual information to characterize room and environment acoustics and noise sources, the audio processing system performing echo cancellation and noise suppression operations to compensate for the identified objects and environmental parameters.
5. The system of claim 4 , wherein:
the environmental characteristics comprise at least one of shape, size, materials, occupant, quantity, location and occlusions.
6. The system of claim 4 , wherein:
the audio processing system performs at least one of beam forming operations, speech input processing operations and de-reverberation operations based upon the information regarding the scene.
7. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
obtaining information regarding a scene from a sensor, the information regarding the scene comprising visual information regarding the scene;
providing the information regarding the scene to an audio processing system; and,
enhancing audio inputs and outputs based upon the information regarding the scene, the enhancing compensating for environment characteristics deduced from the visual information regarding the scene; and wherein
the sensor comprises a camera; and,
the camera comprises front and rear facing cameras, the front facing camera provides a primary input, the primary input providing the information regarding the scene via front facing camera visual information and the rear-facing camera providing additional information to complete the scene, the additional information to complete the scene comprising rear-facing camera visual information, the audio processing system using the front facing camera visual information and rear-facing camera visual information to identify objects located within the scene and the to identify environmental parameters related to the scene, the environmental parameters comprising location parameters, the audio processing system using the front facing camera visual information and the rear-facing camera visual information to characterize room and environment acoustics and noise sources, the audio processing system performing echo cancellation and noise suppression operations to compensate for the identified objects and environmental parameters.
8. The non-transitory, computer-readable storage medium of claim 7 , wherein:
the environmental characteristics comprise at least one of shape, size, materials, occupant, quantity, location and occlusions.
9. The non-transitory, computer-readable storage medium of claim 7 , wherein:
the audio processing system performs at least one of beam forming operations, speech input processing operations and de-reverberation operations based upon the information regarding the scene.
10. The method of claim 1 , wherein:
when generating the front facing camera visual information and rear-facing camera visual information, the sensor performs object recognition operations, motion detection operations, flow detection operations and human detection operations.
11. The system of claim 4 , wherein:
when generating the front facing camera visual information and rear-facing camera visual information, the sensor performs object recognition operations, motion detection operations, flow detection operations and human detection operations.
12. The non-transitory, computer-readable storage medium of claim 7 , wherein:
when generating the front facing camera visual information and rear-facing camera visual information, the sensor performs object recognition operations, motion detection operations, flow detection operations and human detection operations.