Continuous voice sensing

• US 9,508,345 B1
• Filed: 09/24/2014
• Issued: 11/29/2016
• Est. Priority Date: 09/24/2013
• Status: Active Grant

• Current Assignee: Knowles Electronics Llc (Knowles Corporation)
• Original Assignee: Knowles Electronics Llc (Knowles Corporation)
• Inventors: Murgia, Carlo
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US14/495,482
• Time in Patent Office: 797 Days
• Field of Search: 381/92, 381/111, 381/122, 381/57, 700/94, 704/251, 704/231, 704/275
• US Class Current: 1/1
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 1/3215 Monitoring of peripheral devices
• CPC Class Codes: G06F 1/3231 Monitoring the presence, absence or movement of users
• CPC Class Codes: G06F 1/325 Power saving in peripheral device
• CPC Class Codes: G06F 1/3287 by switching off individual functional units in the computer system
• CPC Class Codes: G06F 3/162 Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: H04M 1/6058 involving the use of a headset accessory device connected to the portable telephone
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04R 2430/20 Processing of the output signals of the acoustic transducers of an array for obtaining a desired directivity characteristic H04R2203/12 takes precedence
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407
• CPC Class Codes: H04S 1/007 in which the audio signals are in digital form data reduction aspects thereof based on psychoacoustics G10L19/02
• CPC Class Codes: H04W 52/0254 detecting a user operation or a tactile contact or a motion of the device
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management
• CPC Class Codes: Y02D 30/50 in wire-line communication networks, e.g. low power modes or reduced link rate
• CPC Class Codes: Y02D 30/70 : in wireless communication networks

Abstract

Provided are methods and systems for continuous voice sensing. An example method allows for detecting and buffering, by a first module, a key phrase in an acoustic signal. Responsive to the detection, the method includes sending an interrupt to a second module and switching the first module to an omnidirectional microphone mode. Upon receiving the interrupt, the second module is operable to boot up from a low power mode to an operational mode. While the second module is booting up, the first module is operable to continue to buffer a clean speech output generated from an acoustic signal captured by at least one omnidirectional microphone. After the second module is booted, an indication may be sent to the first module that the second module is ready to exchange data through a fast connection. Upon receiving the indication, the buffered clean speech output may be sent to the second module.

Claims

1. A method for continuous voice sensing comprising:

detecting and buffering, by a first module, a key phrase in an acoustic signal, the acoustic signal including at least one captured sound; and

responsive to the detection;

sending an interrupt to a second module, the second module being responsive to the interrupt to boot up from a low power mode to an operational mode;

while the second module is booting up, continue buffering, by the first module, a clean speech output; and

switching the first module to an omnidirectional microphone mode.

2. The method of claim 1, wherein the interrupt is sent via a General-Purpose Input/Output port.

3. The method of claim 1, wherein the acoustic signal is provided to the first module by at least one Pulse Density Modulation microphone.

4. The method of claim 1, wherein the second module is booted up in substantially 30 ms.

5. The method of claim 1, further comprising after booting up the second module, sending, by the second module to the first module, an indication that the second module is ready to exchange data using at least one of the following interfaces:

SlimBus, Universal Asynchronous Receiver/Transmitter (UART), and System Packet Interface (SPI).

6. The method of claim 1, wherein the clean speech output is generated from a further acoustic signal.

7. The method of claim 6, wherein the further acoustic signal is captured by at least one omnidirectional microphone and wherein the clean speech output is generated as a result of noise suppression or noise reduction.

8. The method of claim 1, further comprising detecting and buffering another key phrase and in response to the detection of both key phrases, triggering at least two different voice search engines, two different recognition engines, or two different applications.

9. The method of claim 1, wherein the detecting and buffering, by the first module, the key phrase in the acoustic signal comprises detecting and buffering separately two key phrases such that clean speech output associated with the two key phrases are provided for respectively launching different voice search engines, different voice recognition engines, or different applications.

10. The method of claim 1, further comprising sending the clean speech output by the first module to the second module.

11. A system for continuous voice sensing comprising:

a first module, the first module operable to;

detect and buffer a key phrase in an acoustic signal, the acoustic signal including at least one captured sound; and

in response to the detection;

send an interrupt to a second module, the second module being responsive to the interrupt to boot up from a low power mode to an operational mode;

while the second module is booting up, continue to buffer, by the first module, a clean speech output; and

switch to an omnidirectional microphone mode.

12. The system of claim 11, wherein the interrupt is sent via a General-Purpose Input/Output port.

13. The system of claim 12, wherein the acoustic signal is provided to the first module by at least one Pulse Density Modulation microphone.

14. The system of claim 11, wherein after booting up, the second module is operable to send to the first module an indication that the second module is ready to exchange data using at least one of the following interfaces:

SlimBus, Universal Asynchronous Receiver/Transmitter (UART), and System Packet Interface (SPI); and

wherein after receiving the indication from the second module, the first module is further operable to send the clean speech output to the second module.

15. The system of claim 11, wherein the clean speech output is generated based on a further acoustic signal.

16. The system of claim 15, wherein the further acoustic signal is captured by at least one omnidirectional microphone and wherein the clean speech output is generated as a result of noise suppression or noise reduction.

17. A non-transitory processor-readable medium having embodied thereon a program being executable by at least one processor to perform a method for continuous voice sensing, the method comprising:

detecting and buffering, by a first module, a key phrase in an acoustic signal, the acoustic signal including at least one captured sound; and

responsive to the detection;

sending an interrupt to a second module, the second module being responsive to the interrupt to boot up from a low power mode to an operational mode;

while the second module is booting up, continue buffering, by the first module, a clean speech output; and

switching the first module to an omnidirectional microphone mode.