SYSTEM AND METHOD FOR CONTROLLING A SPEECH RECOGNITION SYSTEM

• US 20150019074A1
• Filed: 07/15/2014
• Published: 01/15/2015
• Est. Priority Date: 07/15/2013
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Winter, Ute, Hecht, Ron M., Grost, Timothy J., Sims, Robert D.
• Granted Patent: US 9,443,507 B2
• Time in Patent Office: Days
• US Class Current: 701/36
• CPC Class Codes: B60K 2360/148 Instrument input by voice
• CPC Class Codes: B60K 35/10 Input arrangements, i.e. from user to vehicle, associated with vehicle functions or specially adapted therefor
• CPC Class Codes: B60W 2540/21 Voice
• CPC Class Codes: G07C 3/14 Quality control systems
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/226 using non-speech characteristics

Abstract

A method and system can control a speech recognition system in a vehicle. The method includes monitoring adaptive feature data about interactions between a user and the speech recognition system. The method includes determining a first group of samples of the adaptive feature data and creating a control chart based on the first group of samples. The control chart includes a control limit. The method further includes determining a second group of samples of the adaptive feature data after creating the control chart. Furthermore, the method includes calculating an arithmetic mean of each sample of the second group of samples to determine a sample mean, comparing the sample mean to the control limit in order identify unexpected performance of the speech recognition system. The method includes adjusting the speech recognition system based on the identified unexpected performance if the unexpected performance is identified.

Claims

1. A method for controlling a speech recognition system, the method comprising:

monitoring adaptive feature data about interactions between a user and the speech recognition system;

determining, via an adaptive controller, a first group of samples of the adaptive feature data;

creating, via the adaptive controller, a control chart based on the first group of samples, the control chart including a control limit;

determining, via the adaptive controller, a second group of samples of the adaptive feature data after creating the control chart;

calculating, via the adaptive controller, an arithmetic mean of each sample of the second group of samples to determine a sample mean;

comparing, via the adaptive controller, the sample mean to the control limit in order to identify unexpected performance of the speech recognition system; and

if the unexpected performance is identified, then adjusting the speech recognition system based on the identified unexpected performance.

2. The method of claim 1, further comprising updating the control chart with the second group of samples if no unexpected performance is identified.

3. The method of claim 1, wherein the sample mean is a second sample mean, and wherein creating the control chart includes calculating an arithmetic mean of each sample of the first group of samples to determine a first sample mean.

4. The method of claim 3, wherein creating the control chart further includes calculating a standard deviation of each sample of the first group of samples.

5. The method of claim 4, wherein the control limit is a function of the standard deviation.

6. The method of claim 4, wherein the control limit is an upper control limit and the upper control limit is a sum of the first sample mean and a multiple of the standard deviation.

7. The method of claim 6, wherein creating the control chart includes determining a lower control limit, the lower control limit being equal to the first sample mean minus the multiple of the standard deviation.

8. The method of claim 7, wherein comparing the second sample mean includes comparing the second sample mean to the upper control limit and the lower control limit.

9. The method of claim 8, wherein comparing the second sample mean includes identifying statistically unlikely data points of the second sample mean based on at least one of the upper control limit and the lower control limit.

10. The method of claim 9, wherein identifying statistically unlikely data points includes determining if a data point of the second sample mean is greater than the upper control limit.

11. The method of claim 9, wherein identifying statistically unlikely data points includes determining if a data point of the second sample is less than the lower control limit.

12. A system for controlling a speech recognition system, comprising

a human machine interface in communication with the speech recognition system, the human machine interface being configured to receive voice commands and communicate the voice commands to the speech recognition system;

and

an adaptive system in communication with the speech recognition system and the human machine interface, the adaptive system including an adaptive controller and being configured to;

monitor adaptive feature data about interactions between a user and the speech recognition system;

determine, via the adaptive controller, a first group of samples of the adaptive feature data;

create, via the adaptive controller, a control chart based on the first group of samples, the control chart including a control limit;

determine, via the adaptive controller, a second group of samples of the adaptive feature data after creating the control chart;

calculate, via the adaptive controller, an arithmetic mean of each sample of the second group of samples to determine a sample mean;

compare, via the adaptive controller, the sample mean to the control limit in order to identify unexpected performance of the speech recognition system; and

if the unexpected performance is identified, then adjust the speech recognition system based on the identified unexpected performance.

13. The system of claim 12, wherein the adaptive controller is configured to update the control chart with the second group of samples if no unexpected performance is identified.

14. The system of claim 12, wherein the sample mean is a second sample mean, and wherein the adaptive controller is configured to calculate an arithmetic mean of each sample of the first group of samples to determine a first sample mean.

15. The system of claim 14, wherein the adaptive controller is configured to calculate a standard deviation of each sample of the first group of samples.

16. The system of claim 15, wherein the control limit is a function of the standard deviation.

17. The system of claim 16, wherein the control limit is an upper control limit, the upper control limit being a sum of the first sample mean and a multiple of the standard deviation.

18. The system of claim 17, wherein the adaptive controller is configured to calculate a lower control limit, the lower control limit being equal to the first sample mean minus the multiple of the standard deviation.

19. A vehicle, comprising:

a speech recognition system configured to recognize voice commands;

a human machine interface in communication with the speech recognition system, the human machine interface being configured to receive voice commands and communicate the voice commands to the speech recognition system;

an application system in communication with the speech recognition system and configured to receive application commands from the speech recognition system; and

an adaptive system in communication with the speech recognition system and the human machine interface, the adaptive system including an adaptive controller and being configured to;

monitor adaptive feature data about interactions between a user and the speech recognition system;

determine, via the adaptive controller, a first group of samples of the adaptive feature data;

create, via the adaptive controller, a control chart based on the first group of samples, the control chart including a control limit;

determine, via the adaptive controller, a second group of samples of the adaptive feature data after creating the control chart;

calculate, via the adaptive controller, an arithmetic mean of each sample of the second group of samples to determine a sample mean;

compare, via the adaptive controller, the sample mean to the control limit in order to identify unexpected performance of the speech recognition system; and

if the unexpected performance is identified, then adjust the speech recognition system based on the identified unexpected performance.

20. The vehicle of claim 19, wherein the application system is a navigation system.