US 12,114,147 B2
Multi-channel speech compression system and method
Dushyant Sharma, Mountain House, CA (US); Patrick A. Naylor, Reading (GB); and Uwe Helmut Jost, Groton, MA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Feb. 11, 2022, as Appl. No. 17/669,567.
Claims priority of provisional application 63/148,427, filed on Feb. 11, 2021.
Claims priority of provisional application 63/183,848, filed on May 4, 2021.
Prior Publication US 2022/0254358 A1, Aug. 11, 2022
Int. Cl. G10L 15/22 (2006.01); G06T 7/70 (2017.01); G10L 15/06 (2013.01); G10L 19/008 (2013.01); G10L 19/16 (2013.01); G10L 21/0208 (2013.01); H04R 1/40 (2006.01); H04R 3/00 (2006.01); H04R 5/027 (2006.01); H04S 3/00 (2006.01); H04S 7/00 (2006.01); G10L 19/00 (2013.01); G10L 21/0216 (2013.01)
CPC H04S 7/30 (2013.01) [G06T 7/70 (2017.01); G10L 15/063 (2013.01); G10L 15/22 (2013.01); G10L 19/008 (2013.01); G10L 19/167 (2013.01); G10L 21/0208 (2013.01); H04R 1/406 (2013.01); H04R 3/005 (2013.01); H04R 5/027 (2013.01); H04S 3/008 (2013.01); G10L 2019/0001 (2013.01); G10L 2019/0002 (2013.01); G10L 2021/02166 (2013.01); H04R 2201/401 (2013.01); H04S 2400/01 (2013.01); H04S 2400/15 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, executed on a computing device, comprising:
generating a plurality of acoustic relative transfer functions between a plurality of audio acquisition devices of an audio recording system based upon, at least in part, one or more of a predefined speech processing application and a predefined acoustic environment;
generating an acoustic relative transfer function codebook using the plurality of acoustic relative transfer functions; and
encoding selected one or more acoustic relative transfer functions of the plurality of acoustic relative transfer functions into a vector of acoustic relative transfer functions and transmitting the vector of acoustic relative transfer functions and a vector of acoustic relative transfer function codebook entries for the plurality of audio acquisition devices of the audio recording system using the acoustic relative transfer function codebook known to both a front-end speech processing system and a back-end speech processing system.
 
8. 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:
generating a plurality of acoustic relative transfer functions between a plurality of audio acquisition devices of an audio recording system based upon, at least in part, one or more of a predefined speech processing application and a predefined acoustic environment;
generating an acoustic relative transfer function codebook using the plurality of acoustic relative transfer functions; and
encoding selected one or more acoustic relative transfer functions of the plurality of acoustic relative transfer functions into a vector of acoustic relative transfer functions and transmitting the vector of acoustic relative transfer functions and a vector of acoustic relative transfer function codebook entries for the plurality of audio acquisition devices of the audio recording system using the acoustic relative transfer function codebook known to both a front-end speech processing system and a back-end speech processing system.
 
15. A computing system comprising:
a memory; and
a processor configured to generate a plurality of acoustic relative transfer functions between a plurality of audio acquisition devices of an audio recording system based upon, at least in part, one or more of a predefined speech processing application and a predefined acoustic environment, wherein the processor is further configured to generate an acoustic relative transfer function codebook using the plurality of acoustic relative transfer functions, and wherein the processor is further configured to encode selected one or more acoustic relative transfer functions of the plurality of acoustic relative transfer functions into a vector of acoustic relative transfer functions and transmit the vector of acoustic relative transfer functions and a vector of acoustic relative transfer function codebook entries for the plurality of audio acquisition devices of the audio recording system using the acoustic relative transfer function codebook known to both a front-end speech processing system and a back-end speech processing system.