Multi-channel speech compression system and method

1. A computer-implemented method, executed on a computing device, comprising:

obtaining machine vision encounter information using one or more machine vision systems;

obtaining audio encounter information using a plurality of audio acquisition devices of an audio recording system;

encoding the audio encounter information using one or more codecs;

adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information; and

generating a plurality of acoustic relative transfer functions between the plurality of audio acquisition devices of the audio recording system,

wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to encode the audio encounter information using one or more acoustic relative transfer functions associated with a particular acoustic source when the machine vision encounter information detects the acoustic source.

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 adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to estimate one or more acoustic relative transfer functions when the machine vision encounter information indicates at least a threshold change in the acoustic environment.

4. The computer-implemented method of claim 1 , wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to selectively encode the audio encounter information based upon, at least in part, whether the machine vision encounter information indicates that an audio source is speaking.

5. The computer-implemented method of claim 1 , wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to generate the plurality of acoustic relative transfer functions between the plurality of audio acquisition devices of the audio recording system based upon, at least in part, location information associated with an acoustic source from the machine vision encounter information.

6. A computer program product residing on 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:

obtaining machine vision encounter information using one or more machine vision systems;

obtaining audio encounter information using a plurality of audio acquisition devices of an audio recording system;

encoding the audio encounter information using one or more codecs;

adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information; and

generating a plurality of acoustic relative transfer functions between the plurality of audio acquisition devices of the audio recording system,

wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to encode the audio encounter information using one or more acoustic relative transfer functions associated with a particular acoustic source when the machine vision encounter information detects the acoustic source.

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 adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to estimate one or more acoustic relative transfer functions when the machine vision encounter information indicates at least a threshold change in the acoustic environment.

9. The computer program product of claim 6 , wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to selectively encode the audio encounter information based upon, at least in part, whether the machine vision encounter information indicates that an audio source is speaking.

10. The computer program product of claim 6 , wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to generate the plurality of acoustic relative transfer functions between the plurality of audio acquisition devices of the audio recording system based upon, at least in part, location information associated with an acoustic source from the machine vision encounter information.

11. A computing system comprising:

a memory; and

a processor configured to obtain machine vision encounter information using one or more machine vision systems, wherein the processor is further configured to obtain audio encounter information using a plurality of audio acquisition devices of an audio recording system, wherein the processor is further configured to encode the audio encounter information using one or more codecs, wherein the processor is further configured to adapt the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information, wherein the processor is further configured to generate a plurality of acoustic relative transfer functions between the plurality of audio acquisition devices of the audio recording system, and wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to encode the audio encounter information using one or more acoustic relative transfer functions associated with a particular acoustic source when the machine vision encounter information detects the acoustic source.

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 adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to estimate one or more acoustic relative transfer functions when the machine vision encounter information indicates at least a threshold change in the acoustic environment.

14. The computing system of claim 11 , wherein adapting the encoding of the audio encounter information by the one or more codecs based upon, at least in part, the machine vision encounter information includes adapting the one or more codecs to selectively encode the audio encounter information based upon, at least in part, whether the machine vision encounter information indicates that an audio source is speaking.