Multi-channel speech compression system and method
A method, computer program product, and computing system for generating a plurality of acoustic relative transfer functions associated with a plurality of audio acquisition devices of an audio recording system deployed in an acoustic environment. At least a pair of the plurality of acoustic relative transfer functions from time frames may be compared. A change in the acoustic environment may be detected based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames.
1. A computer-implemented method, executed on a computing device, comprising:
generating a plurality of acoustic relative transfer functions associated with a plurality of audio acquisition devices of an audio recording system deployed in an acoustic environment, wherein generating the plurality of acoustic relative transfer functions includes generating a plurality of residual signals associated with the plurality of audio acquisition devices based upon, at least in part, the acoustic relative transfer functions for each audio acquisition device of the plurality of audio acquisition devices;
comparing the plurality of acoustic relative transfer functions from at least a pair of time frames; and
detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames from the plurality of acoustic relative transfer functions, wherein detecting the change in the acoustic environment includes:
comparing the plurality of residual signals from at least a pair of time frames; and
detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of residual signals from at least the pair of time frames.
2. The computer-implemented method of claim 1 , wherein the plurality of audio acquisition devices of the audio recording system are positioned within a fixed geometry relative to each other.
3. The computer-implemented method of claim 1 , wherein detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames includes determining at least a threshold change in the acoustic relative transfer functions between the at least a pair of time frames.
4. The computer-implemented method of claim 1 , further comprising:
training a machine learning model to output a change classification based upon, at least in part, the plurality of acoustic relative transfer functions from at least the pair of time frames.
5. The computer-implemented method of claim 4 , wherein detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames includes detecting the change in the acoustic environment using the trained machine learning model.
6. A computer program product comprising a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
generating a plurality of acoustic relative transfer functions associated with a plurality of audio acquisition devices of an audio recording system deployed in an acoustic environment, wherein generating the plurality of acoustic relative transfer functions includes generating a plurality of residual signals associated with the plurality of audio acquisition devices based upon, at least in part, the acoustic relative transfer functions for each audio acquisition device of the plurality of audio acquisition devices;
comparing the plurality of acoustic relative transfer functions from at least a pair of time frames; and
detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames from the plurality of acoustic relative transfer functions, wherein detecting the change in the acoustic environment includes:
comparing the plurality of residual signals from at least a pair of time frames; and
detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of residual signals from at least the pair of time frames.
7. The computer program product of claim 6 , wherein the plurality of audio acquisition devices of the audio recording system are positioned within a fixed geometry relative to each other.
8. The computer program product of claim 6 , wherein detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames includes determining at least a threshold change in the acoustic relative transfer functions between the at least a pair of time frames.
9. The computer program product of claim 6 , wherein the operations further comprise: training a machine learning model to output a change classification based upon, at least in part, the plurality of acoustic relative transfer functions from at least the pair of time frames.
10. The computer program product of claim 9 , wherein detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames includes detecting the change in the acoustic environment using the trained machine learning model.
11. A computing system comprising:
a memory; and
a processor configured to generate a plurality of acoustic relative transfer functions associated with a plurality of audio acquisition devices of an audio recording system deployed in an acoustic environment, wherein generating the plurality of acoustic relative transfer functions includes generating a plurality of residual signals associated with the plurality of audio acquisition devices based upon, at least in part, the acoustic relative transfer functions for each audio acquisition device of the plurality of audio acquisition devices, wherein the processor is further configured to compare the plurality of acoustic relative transfer functions from at least a pair of time frames, and wherein the processor is further configured to detect a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames from the plurality of acoustic relative transfer functions, wherein detecting the change in the acoustic environment includes: comparing the plurality of residual signals from at least a pair of time frames, and detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of residual signals from at least the pair of time frames.
12. The computing system of claim 11 , wherein the plurality of audio acquisition devices of the audio recording system are positioned within a fixed geometry relative to each other.
13. The computing system of claim 11 , wherein detecting a change in the acoustic environment based upon, at least in part, the comparison of at least the pair of time frames from the plurality of acoustic relative transfer functions includes determining at least a threshold change in the acoustic relative transfer functions between the at least a pair of time frames.
14. The computing system of claim 11 , wherein the processor is further configured to:
train a machine learning model to output a change classification based upon, at least in part, the plurality of acoustic relative transfer functions from at least the pair of time frames.
15. The computing system of claim 14 , wherein detecting a change in the acoustic environment based upon, at least in part, the comparison of the plurality of acoustic relative transfer functions from at least the pair of time frames includes detecting the change in the acoustic environment using the trained machine learning model.