IP Library Granted Patent US 11,783,826
Granted Patent B2
US 11,783,826 · App. 17/178,785 · Granted Oct 10, 2023

System and method for data augmentation and speech processing in dynamic acoustic environments

Inventors: Patrick A. Naylor (Reading, GB); Dushyant Sharma (Woburn, MA); Uwe Helmut Jost (Groton, MA); William F. Ganong, III (Brookline, MA)
Assignee: Nuance Communications, Inc.
G10L15/22G10L15/063G10L21/0224G10L21/0332G10L2021/02166
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,783,826
App. No.
17/178,785
Granted
Oct 10, 2023
Kind
B2
Abstract

A method, computer program product, and computing system for receiving one or more inputs indicative of at least one of: a relative location of a speaker and a microphone array, and a relative orientation of the speaker and the microphone array. One or more reference signals may be received. A speech processing system may be trained using the one or more inputs and the one or more reference signals.

Claims (48)

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

receiving one or more inputs indicative of at least one of:

a relative location of a speaker and a microphone array, and

a relative orientation of the speaker and the microphone array;

receiving one or more reference signals; and

training a speech processing system using the one or more inputs and the one or more reference signals, wherein training the speech processing system using the one or more inputs and the one or more reference signals includes training a plurality of speech processing models for a plurality of acoustic variations associated with the one or more reference signals;

receiving one or more run-time inputs indicative of at least one of:

the relative location of the speaker and the microphone array, and

the relative orientation of the speaker and the microphone array;

receiving a speech signal via the microphone array; and

performing speech processing via the trained speech processing system using the one or more run-time inputs and the speech signal.

2. The computer-implemented method of claim 1 , wherein receiving the one or more inputs includes one or more of:

receiving the one or more inputs from one or more sensors positioned within a monitored space; and

generating the one or more inputs.

3. The computer-implemented method of claim 1 , wherein receiving the one or more reference signals includes one or more of:

receiving one or more speech signals via the microphone array; and

generating one or more time-varying spectrally-augmented signals.

4. The computer-implemented method of claim 3 , wherein training the speech processing system using the one or more inputs and the one or more reference signals includes training the speech processing system using the one or more speech signals received via the microphone array and the one or more generated time-varying spectrally-augmented signals.

5. The computer-implemented method of claim 1 , wherein performing speech processing via the trained speech processing system using the one or more run-time inputs and the speech signal includes selecting at least one trained speech processing model from the plurality of trained speech processing models based upon, at least in part, the one or more run-time inputs and the speech signal.

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:

receiving one or more inputs indicative of at least one of:

a relative location of a speaker and a microphone array, and

a relative orientation of the speaker and the microphone array;

receiving one or more reference signals; and

training a speech processing system using the one or more inputs and the one or more reference signals, wherein training the speech processing system using the one or more inputs and the one or more reference signals includes training a plurality of speech processing models for a plurality of acoustic variations associated with the one or more reference signals;

receiving one or more run-time inputs indicative of at least one of:

the relative location of the speaker and the microphone array, and

the relative orientation of the speaker and the microphone array;

receiving a speech signal via the microphone array; and

performing speech processing via the trained speech processing system using the one or more run-time inputs and the speech signal.

7. The computer program product of claim 6 , wherein receiving the one or more inputs includes one or more of:

receiving the one or more inputs from one or more sensors positioned within a monitored space; and

generating the one or more inputs.

8. The computer program product of claim 6 , wherein receiving the one or more reference signals includes one or more of:

receiving one or more speech signals via the microphone array; and

generating one or more time-varying spectrally-augmented signals.

9. The computer program product of claim 8 , wherein training the speech processing system using the one or more inputs and the one or more reference signals includes training the speech processing system using the one or more speech signals received via the microphone array and the one or more generated time-varying spectrally-augmented signals.

10. The computer program product of claim 6 , wherein performing speech processing via the trained speech processing system using the one or more run-time inputs and the speech signal includes selecting at least one trained speech processing model from the plurality of trained speech processing models based upon, at least in part, the one or more run-time inputs and the speech signal.

11. A computing system comprising:

a memory; and

a processor configured to receive one or more inputs indicative of at least one of: a relative location of a speaker and a microphone array, and a relative orientation of the speaker and the microphone array; wherein the processor is further configured to receive one or more reference signals; and wherein the processor is further configured to train a speech processing system using the one or more inputs and the one or more reference signals, wherein training the speech processing system using the one or more inputs and the one or more reference signals includes training a plurality of speech processing models for a plurality of acoustic variations associated with the one or more reference signals, wherein the processor is further configured to receive one or more run-time inputs indicative of at least one of the relative location of the speaker and the microphone array, and the relative orientation of the speaker and the microphone array, wherein the processor is further configured to receive a speech signal via the microphone array, and wherein the processor is further configured to perform speech processing via the trained speech processing system using the one or more run-time inputs and the speech signal.

12. The computing system of claim 11 , wherein receiving the one or more inputs includes one or more of:

receiving the one or more inputs from one or more sensors positioned within a monitored space; and

generating the one or more inputs.

13. The computing system of claim 11 , wherein receiving the one or more reference signals includes one or more of:

receiving one or more speech signals via the microphone array; and

generating one or more time-varying spectrally-augmented signals.

14. The computing system of claim 13 , wherein training the speech processing system using the one or more inputs and the one or more reference signals includes training the speech processing system using the one or more speech signals received via the microphone array and the one or more generated time-varying spectrally-augmented signals.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 14, 2023
From: NUANCE COMMUNICATIONS, INC.
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 065578/0676 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 18, 2021
From: NAYLOR, PATRICK A.; SHARMA, DUSHYANT; JOST, UWE HELMUT; GANONG III, WILLIAM F.
To: NUANCE COMMUNICATIONS, INC.
Reel/Frame 055320/0985 →
Continuity (1)
Related Publication 20220262357A1 · Aug 18, 2022