Voice command conversion

• US 10,109,182 B1
• Filed: 07/18/2017
• Issued: 10/23/2018
• Est. Priority Date: 07/20/2016
• Status: Active Grant

• Current Assignee: DSP Group Ltd. (Synaptics Incorporated)
• Original Assignee: DSP Group Ltd. (Synaptics Incorporated)
• Inventors: Yehuday, Uri
• Primary Examiner(s): Blouin, Mark
• Application Number:
  US15/652,338
• Time in Patent Office: 462 Days
• Field of Search: 367198
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G08C 2201/31 Voice input
• CPC Class Codes: G08C 23/02 using infrasonic, sonic or ultrasonic waves
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 21/0232 Processing in the frequency domain

Abstract

A method and a system for voice command conversion, the system may include one or more microphones for sensing a voice command for controlling an acoustically controlled device; one or more speech recognition units for identifying the voice command; an ultrasonic command generator for generating an ultrasonic command that represents the voice command; and one or more speakers for transmitting the ultrasonic command to the acoustically controlled device.

Claims

1. A system for voice command conversion, the system comprises:

one or more microphones for sensing a voice command for controlling an acoustically controlled device;

one or more speech recognition units for identifying the voice command;

an ultrasonic command generator for generating an ultrasonic command that represents the voice command; and

one or more speakers for transmitting the ultrasonic command to the acoustically controlled device.

2. The system according to claim 1 wherein the one or more microphones, the one or more speech recognition units, the ultrasonic command generator and the one or more speakers are included in an intermediate device that is included in a single housing.

3. The system according to claim 2, comprising one or more sensors for tracking an execution of the voice command by the acoustically controlled device.

4. The system according to claim 3 wherein the one or more sensors differ from the one or more microphones.

5. The system according to claim 3 wherein the one or more sensors comprise at least one image sensor.

6. The system according to claim 3 wherein the one or more sensors comprise at least one movement sensor.

7. The system according to claim 3 wherein the one or more sensors are the one or more microphones.

8. The system according to claim 1 wherein the ultrasonic generator is configured to generate the ultrasonic command, following the identifying of the voice command by the one or more speech recognition units, by searching an ultrasonic command that corresponds to the voice command.

9. The system according to claim 1 wherein the ultrasonic generator is configured to generate the ultrasonic command, following the identifying of the voice command by the one or more speech recognition units, by retrieving from another device the ultrasonic command.

10. The system according to claim 1 wherein the ultrasonic generator is configured to generate the ultrasonic command, following the identifying of the voice command by the one or more speech recognition units, by using a mapping between voice commands and ultrasonic commands.

11. The system according to claim 1, wherein the system is configured to evaluate a validity of the voice command and to generate the ultrasonic command only when determining that the voice command is valid.

12. The system according to claim 11 wherein the system is constructed and arranged to evaluate the validity of the voice command by checking whether the voice command belongs to a set of voice commands associated with the acoustically controlled device.

13. The system according to claim 1, wherein the system is configured to evaluate a validity of the voice command and to generate the ultrasonic command regardless of the validity of the voice command.

14. The system according to claim 1, wherein the system is configured to transmit the ultrasonic command only when the acoustically controlled device did not respond to the voice command.

15. The system according to claim 14 wherein the system is constructed and arranged to determine that the acoustically controlled device did not respond to the voice command by detecting that a person that issued the voice command repeated the voice command several times.

16. The system according to claim 14 wherein the system is constructed and arranged to determine that the acoustically controlled device did not respond to the voice command by detecting a lack of response from the acoustically controlled device.

17. The system according to claim 16 wherein the system is constructed and arranged to detect a lack of response from the acoustically controlled device by sensing noise generated by the acoustically controlled device.

18. The system according to claim 16 wherein the system is constructed and arranged to detect a lack of response from the acoustically controlled device by sensing movement or lack of movement by the acoustically controlled device.

19. The system according to claim 1 comprising one or more spectrum analyzers for finding a gap in a spectrum of an actual noise generated by the acoustically controlled device or an expected noise generated by the acoustically controlled device;

and wherein the ultrasonic command generator is configured to select an ultrasonic frequency of ultrasonic command to fall in the gap.

20. The system according to claim 1 comprising one or more spectrum analyzers for finding a gap in a spectrum of an actual noise generated by an environment of the system or an expected noise generated by the environment of the system;

and wherein the ultrasonic command generator is configured to select an ultrasonic frequency of ultrasonic command to fall in the gap.

21. The system according to claim 1 comprising one or more spectrum analyzers for finding frequency range in a spectrum of noise generated by the acoustically controlled device in which the noise is below a predefined threshold;

and wherein the ultrasonic command generator is configured to select an ultrasonic frequency of ultrasonic command to fall in the frequency range.

22. The system according to claim 1 comprising one or more spectrum analyzers for finding frequency range in a spectrum of noise generated by an environment of the system in which the noise is below a predefined threshold;

and wherein the ultrasonic command generator is configured to select an ultrasonic frequency of ultrasonic command to fall in the frequency range.

23. The system according to claim 1 wherein the acoustically controlled device is a speaker and the system comprises a music identifier for identifying music that is played by the speaker and to determine an ultrasonic frequency of the ultrasonic command based on the music played by the speaker to fit in at least one gap or in frequencies of less spectral content of the music played by the speaker.

24. A method for voice command conversion, the method comprises:

sensing, by one or more microphones, a voice command for controlling an acoustically controlled device;

identifying, by one or more speech recognition units, the voice command;

generating, by an ultrasonic command generator, an ultrasonic command that represents the voice command; and

transmitting, by one or more speakers, the ultrasonic command to the acoustically controlled device.

25. The method according to claim 24 wherein the one or more microphones, the one or more speech recognition units, the ultrasonic command generator and the one or more speakers are included in an intermediate device that is included in a single housing.

26. The method according to claim 25 comprising tracking an execution of the voice command by the acoustically controlled device.

27. The method according to claim 25 comprising determining that the acoustically controlled device did not respond to the voice command by detecting that a person that issued the voice command repeated the voice command several times.

28. The method according to claim 25 comprising determining that the acoustically controlled device did not respond to the voice command by detecting a lack of response from the acoustically controlled device.

29. The method according to claim 24, comprising evaluating a validity of the voice command and generating the ultrasonic command only when determining that the voice command is valid.

30. The method according to claim 29 wherein the evaluating of the validity of the voice command comprises checking whether the voice command belongs to a set of voice commands associated with the acoustically controlled device.

31. The method according to claim 24 wherein the acoustically controlled device is a speaker, wherein the method comprises identifying, by a music identifier, music that is played by the speaker;

and determining an ultrasonic frequency of the ultrasonic command based on the music played by the speaker to fit in at least one gap or in frequencies of less spectral content of the music played by the speaker.

32. The method according to claim 24, wherein the method is executed by a system, wherein the method comprises finding, by one or more spectrum analyzers, a gap in a spectrum;

and selecting, by the ultrasonic command generator, an ultrasonic frequency of ultrasonic command to fall in the gap; and

wherein the spectrum is selected out of;

(a) a spectrum of an actual noise generated by the acoustically controlled device, (b) a spectrum of an expected noise generated by the acoustically controlled device, (c) a spectrum of an actual noise generated by an environment of the system;

(d) a spectrum of or an expected noise generated by the environment of the system;

(e) in a spectrum of noise generated by the acoustically controlled device in which the noise is below a predefined threshold, (f) a spectrum of noise generated by an environment of the system in which the noise is below a predefined threshold.