SPEECH RECOGNITION WAKE-UP OF A HANDHELD PORTABLE ELECTRONIC DEVICE
First Claim
1. A handheld portable electronic device comprising:
- a plurality of microphones to pickup speech of a user, including a first microphone differently positioned than a second microphone;
a long phrase recognition processor communicatively coupled with the plurality of microphones and having an activated state and a deactivated state; and
a short phrase recognition processor having a plurality of speech recognition, SR, engines to remain activated while the long phrase recognition processor is in the deactivated state, the plurality of SR engines to receive a plurality of audio signals, respectively, from the plurality of microphones, respectively, so that the audio signals are processed in parallel by the SR engines, respectively, to recognize a command in any one of the respective audio signals, the short phrase processor to signal the long phrase processor to transition from the deactivated state to the activated state in response to any one of the SR engines recognizing the command in its respective audio signal.
1 Assignment
0 Petitions
Accused Products
Abstract
A system and method for parallel speech recognition processing of multiple audio signals produced by multiple microphones in a handheld portable electronic device. In one embodiment, a primary processor transitions to a power-saving mode while an auxiliary processor remains active. The auxiliary processor then monitors the speech of a user of the device to detect a wake-up command by speech recognition processing the audio signals in parallel. When the auxiliary processor detects the command it then signals the primary processor to transition to active mode. The auxiliary processor may also identify to the primary processor which microphone resulted in the command being recognized with the highest confidence. Other embodiments are also described.
308 Citations
18 Claims
-
1. A handheld portable electronic device comprising:
-
a plurality of microphones to pickup speech of a user, including a first microphone differently positioned than a second microphone; a long phrase recognition processor communicatively coupled with the plurality of microphones and having an activated state and a deactivated state; and a short phrase recognition processor having a plurality of speech recognition, SR, engines to remain activated while the long phrase recognition processor is in the deactivated state, the plurality of SR engines to receive a plurality of audio signals, respectively, from the plurality of microphones, respectively, so that the audio signals are processed in parallel by the SR engines, respectively, to recognize a command in any one of the respective audio signals, the short phrase processor to signal the long phrase processor to transition from the deactivated state to the activated state in response to any one of the SR engines recognizing the command in its respective audio signal. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method in a handheld portable electronic device, comprising:
-
activating an auxiliary processor; deactivating a primary processor; monitoring, using the activated auxiliary processor and while the primary processor remains deactivated, speech of a user through a plurality of microphones that are differently positioned from one another in the handheld portable electronic device, wherein the activated auxiliary processor performs in parallel a separate automatic speech recognition (ASR) process upon each signal from the plurality of microphones; detecting a command by the ASR process associated with a first microphone of the plurality; and activating the primary processor in response to the detecting of the command by the activated auxiliary processor. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A method in a handheld portable electronic device, comprising:
-
transitioning the handheld portable electronic device into sleep mode; while in the sleep mode, detecting a command spoken by a user of the handheld portable electronic device using any one of a plurality of microphones within the handheld portable electronic device based on having performed a separate automatic speech recognition (ASR) process upon each signal from the plurality of microphones; transitioning the handheld portable electronic device from the sleep mode to awake mode in response to the detecting of the command. - View Dependent Claims (16, 17, 18)
-
Specification