Multi-channel speech compression system and method
A method, computer program product, and computing system for encoding audio encounter information of a reference audio acquisition device of a plurality of audio acquisition devices of an audio recording system, thus defining encoded reference audio encounter information. Location information may be estimated, via a machine vision system, for an acoustic source within an acoustic environment. One or more acoustic relative transfer functions may be selected from a plurality of acoustic relative transfer functions for the plurality of audio acquisition devices of the audio recording system based upon, at least in part, the location information. The encoded reference audio encounter information and a representation of the selected one or more acoustic relative transfer function may be transmitted.
1. A computer-implemented method, executed on a computing device, comprising:
encoding audio encounter information of a reference audio acquisition device of a plurality of audio acquisition devices of an audio recording system, thus defining encoded reference audio encounter information;
estimating, via a machine vision system, location information for an acoustic source within an acoustic environment;
accessing an acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system, wherein the acoustic relative transfer function codebook includes a plurality of acoustic relative transfer functions between the reference audio acquisition device and the plurality of audio acquisition devices of the audio recording system, wherein each of the plurality of acoustic relative transfer functions is associated with a unique identifier for being uniquely identifiable from the plurality of acoustic relative transfer functions of the acoustic relative transfer function codebook based upon, at least in part, the location information and speakers within the acoustic environment, and wherein the acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system includes a data structure configured to store mapping characteristics for mapping speech signals obtained by the reference audio acquisition device to speech signals of another audio acquisition device of the plurality of audio acquisition devices;
selecting one or more acoustic relative transfer functions from the acoustic relative transfer function codebook based upon, at least in part, the location information; and
transmitting the encoded reference audio encounter information and a representation of the selected one or more acoustic relative transfer functions.
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 , further comprising:
mapping the location information for the acoustic source within the acoustic environment to the plurality of acoustic relative transfer functions, wherein the one or more acoustic relative transfer functions are selected from the acoustic relative transfer function codebook based on the mapping of the location information to the plurality of acoustic relative transfer functions.
4. The computer-implemented method of claim 1 , wherein accessing the acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system includes generating a plurality of residual signals associated with the selected one or more acoustic relative transfer functions.
5. The computer-implemented method of claim 1 , wherein the representation of the selected one or more acoustic relative transfer functions includes a vector generated by encoding the selected one or more acoustic relative transfer functions.
6. The computer-implemented method of claim 1 , wherein the representation of the selected one or more acoustic relative transfer functions includes a vector generated by encoding one or more codebook entries within the acoustic relative transfer function codebook, the one or more codebook entries corresponding to the selected one or more acoustic relative transfer functions.
7. The computer-implemented method of claim 1 , wherein the machine vision system includes red, green, blue (RGB) sensors.
8. The computer-implemented method of claim 1 , wherein the machine vision system includes infrared sensors.
9. The computer-implemented method of claim 1 , wherein the machine vision system includes ultraviolet sensors.
10. The computer-implemented method of claim 1 , wherein the machine vision system includes SONAR sensors.
11. The computer-implemented method of claim 1 , wherein the machine vision system includes RADAR sensors.
12. The computer-implemented method of claim 1 , wherein the machine vision system includes thermal imaging sensors.
13. A non-transitory 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:
encoding audio encounter information of a reference audio acquisition device of a plurality of audio acquisition devices of an audio recording system, thus defining encoded reference audio encounter information;
estimating, via a machine vision system, location information for an acoustic source within an acoustic environment;
accessing an acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system, wherein the acoustic relative transfer function codebook includes a plurality of acoustic relative transfer functions between the reference audio acquisition device and the plurality of audio acquisition devices of the audio recording system, wherein each of the plurality of acoustic relative transfer functions is associated with a unique identifier for being uniquely identifiable from the plurality of acoustic relative transfer functions of the acoustic relative transfer function codebook based upon, at least in part, the location information and speakers within the acoustic environment, wherein the acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system includes a data structure configured to store mapping characteristics for mapping speech signals obtained by the reference audio acquisition device to speech signals of another audio acquisition device of the plurality of audio acquisition devices;
selecting one or more acoustic relative transfer functions from the acoustic relative transfer function codebook based upon, at least in part, the location information; and
transmitting the encoded reference audio encounter information and a representation of the selected one or more acoustic relative transfer functions.
14. The non-transitory computer program product of claim 13 , wherein the plurality of audio acquisition devices of the audio recording system are positioned within a fixed geometry relative to each other.
15. The non-transitory computer program product of claim 13 , wherein the operations further comprise:
mapping the location information for the acoustic source within the acoustic environment to the plurality of acoustic relative transfer functions, wherein the one or more acoustic relative transfer functions are selected from the acoustic relative transfer function codebook based on the mapping of the location information to the plurality of acoustic relative transfer functions.
16. The non-transitory computer program product of claim 13 , wherein accessing the acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system includes generating a plurality of residual signals associated with the selected one or more acoustic relative transfer functions.
17. A computing system comprising:
a memory storing programming instructions; and
a processor configured to execute the programming instructions stored in the memory, wherein the programming instructions, upon execution by the processor, cause the system to:
encode audio encounter information of a reference audio acquisition device of a plurality of audio acquisition devices of an audio recording system, thus defining encoded reference audio encounter information;
estimate, via a machine vision system, location information for an acoustic source within an acoustic environment;
access an acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system, wherein the acoustic relative transfer function codebook includes a plurality of acoustic relative transfer functions between the reference audio acquisition device and the plurality of audio acquisition devices of the audio recording system, wherein each of the plurality of acoustic relative transfer functions is associated with a unique identifier for being uniquely identifiable from the plurality of acoustic relative transfer functions of the acoustic relative transfer function codebook based upon, at least in part, the location information and speakers within the acoustic environment, and wherein the acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system includes a data structure configured to store mapping characteristics for mapping speech signals obtained by the reference audio acquisition device to speech signals of another audio acquisition device of the plurality of audio acquisition devices;
select one or more acoustic relative transfer functions from the acoustic relative transfer function codebook based upon, at least in part, the location information; and
transmit the encoded reference audio encounter information and the selected one or more acoustic relative transfer functions corresponding to the encoded reference audio information.
18. The computing system of claim 17 , wherein the plurality of audio acquisition devices of the audio recording system are positioned within a fixed geometry relative to each other.
19. The computing system of claim 17 , wherein the processor is further configured to:
map the location information for the acoustic source within the acoustic environment to the plurality of acoustic relative transfer functions, wherein the one or more acoustic relative transfer functions are selected from the acoustic relative transfer function codebook based on the mapping of the location information to the plurality of acoustic relative transfer functions.
20. The computing system of claim 17 , wherein accessing the acoustic relative transfer function codebook for the plurality of audio acquisition devices of the audio recording system includes generating a plurality of residual signals associated with the selected one or more acoustic relative transfer functions.