Methods and apparatus for detecting a voice command

Patent metadata

Field	Value
Publication number	US-12548565-B2
Application number	US-202217867091-A
Country	US
Kind code	B2
Filing date	Jul 18, 2022
Priority date	Mar 12, 2013
Publication date	Feb 10, 2026
Grant date	Feb 10, 2026

Abstract

According to some aspects, a method of monitoring an acoustic environment of a mobile device, at least one computer readable medium encoded with instructions that, when executed, perform such a method and/or a mobile device configured to perform such a method is provided. The method comprises receiving acoustic input from the environment of the mobile device while the mobile device is operating in the low power mode, detecting whether the acoustic input includes a voice command based on performing a plurality of processing stages on the acoustic input, wherein at least one of the plurality of processing stages is performed while the mobile device is operating in the low power mode, and using at least one contextual cue to assist in detecting whether the acoustic input includes a voice command.

First claim

What is claimed is:

1 . A method for detecting a voice command by a mobile device having a plurality of processors and a plurality of microphones, the method comprising:
receiving, via a first microphone, an acoustic input while a primary processor and a second microphone are inactive and a secondary processor is active; processing, via the secondary processor, the acoustic input to determine whether the acoustic input relates to a spurious acoustic activity; responsive to the acoustic input not relating the spurious acoustic activity, activating the primary processor; and processing, via the primary processor, the acoustic input to detect a voice command based on at least one contextual cue without using a trigger word.

2 . The method of claim 1 , further comprising: activating the second microphone while the primary processor is inactive in response to the acoustic input exceeding a threshold.

3 . The method of claim 2 , wherein the threshold includes at least one of a volume amplitude, a time duration, or an acoustic energy.

4 . The method of claim 1 , further comprising: activating the second microphone in response to detecting the voice command in the acoustic input.

5 . The method of claim 1 , further comprising: processing, via the primary processor, the acoustic input to detect a voice command based on at least one of a volume of the acoustic input, or an energy of the acoustic input.

6 . The method of claim 1 , wherein the spurious acoustic activity includes a speech uttered by a non-recognized user voice.

7 . The method of claim 1 , wherein the spurious acoustic activity includes a speech not corresponding to any voice command.

8 . The method of claim 1 , wherein the at least one contextual cue includes at least one of: time of day, motion of the device, location of the device, an occurrence of an event on the device, recent activity on the device, and state of a battery powering the device.

9 . A mobile device, comprising:
a first microphone; a second microphone; a primary processor; and a secondary processor programmed to: responsive to receiving, via a first microphone, an acoustic input while a primary processor and a second microphone are inactive, compare the acoustic input with a threshold, and responsive to detecting the acoustic input exceeds the threshold, instruct the second microphone to activate while the primary processor is still inactive, wherein the primary processor is programmed to: detect a voice command in the acoustic input based on at least one contextual cue without using a trigger word.

10 . The mobile device of claim 9 , wherein the secondary processor is further programmed to:
process the acoustic input to determine whether the acoustic input relates to a spurious acoustic activity; and responsive to the acoustic input not relating the spurious acoustic activity, instructing the primary processor to activate.

11 . The mobile device of claim 10 , wherein the spurious acoustic activity includes a speech uttered by a non-recognized user voice.

12 . The mobile device of claim 10 , wherein the spurious acoustic activity includes a speech not corresponding to any voice command.

13 . The mobile device of claim 9 , wherein the threshold includes at least one of a volume amplitude, a time duration, or an acoustic energy.

14 . The mobile device of claim 9 , wherein the secondary processor is further programmed to: activate the second microphone response to detecting the voice command in the acoustic input.

15 . The mobile device of claim 9 , wherein the primary processor is programmed to: detect a voice command in the acoustic input based on at least one of a volume of the acoustic input, or an energy of the acoustic input.

16 . A non-transitory computer readable medium encoded with instructions that, when executed on at least one processor, perform a method of monitoring an acoustic environment of a mobile device to receive acoustic input in multiple stages including in a low power stage and normal power stage, the method comprising:
receiving, via a first microphone, an acoustic input in the low power stage while a primary processor and a second microphone are inactive and a secondary processor is active;
processing, in the lower power stage, the acoustic input to determine whether the acoustic input relates to a spurious acoustic activity;
responsive to the acoustic input not relating the spurious acoustic activity, activating the primary processor to enter into the normal power stage; and
processing, in the normal power stage, the acoustic input to detect a voice command based on at least one contextual cue without using a trigger word.

17 . The non-transitory computer readable medium of claim 16 , wherein the method further comprising:
activating the second microphone, in the low power stage, in response to the acoustic input exceeding a threshold.

18 . The non-transitory computer readable medium of claim 17 , wherein the threshold includes a volume amplitude and a time duration.

19 . The non-transitory computer readable medium of claim 16 , wherein the method further comprising:
activating the second microphone response to detecting the voice command in the acoustic input.

20 . The non-transitory computer readable medium of claim 16 , wherein the spurious acoustic activity includes a speech uttered by a non-recognized user voice.

Assignees

• Cerence Operating Co

Inventors

• Ganong Iii William F
• Van Mulbregt Paul A
• Sejnoha Vladimir
• Wilson Glen

Classifications

• H04W88/02

  Terminal devices · CPC title

• H04W52/0261

  managing power supply demand, e.g. depending on battery level · CPC title

• H04W40/005

  Routing actions in the presence of nodes in sleep or doze mode · CPC title

• G10L2015/226

  using non-speech characteristics · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title