Unlock instant, AI-driven research and patent intelligence for your innovation.

Voice command processing in low power devices

A voice command and audio processing technology, applied in voice analysis, voice recognition, data processing power supply, etc., can solve problems such as slowing down

Pending Publication Date: 2020-08-21
SYNAPTICS INC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In other devices, a processing delay may be introduced that may cause the user to slow down or otherwise alter the voice pattern so that the initial voice command can be received

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice command processing in low power devices
  • Voice command processing in low power devices
  • Voice command processing in low power devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The methods and apparatus of the present invention provide improved techniques for processing audio samples in low power voice controlled devices. In various embodiments, audio received during a sleep mode, low power mode, or wakeup sequence is processed by the host device with low latency.

[0012] During operation, voice-controlled devices often wait for a keyword to be spoken to trigger further voice command processing. To save power, some devices include a host processor that is placed in sleep mode during periods of inactivity, while audio input is routed to a low power digital signal processor (DSP). A low power DSP receives the audio input and runs a lower power trigger engine to detect keywords. After detecting the keyword, the DSP transmits a wake-up signal to the high-power host processor. In various embodiments, the host system may include a high-performance trigger engine that revalidates keywords to ensure that keywords have been detected, a high-performa...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An audio processing device comprises audio input circuitry operable to receive audio input signals and to process the audio input signals to generate audio samples at a first rate. The audio processing device further comprises a first trigger engine operable to detect a keyword within the audio samples. Also, the audio processing device comprises a delay buffer operable to continuously receive andstore the audio samples. The delay buffer is further operable to transfer the audio samples that are stored within the delay buffer to a host across a data bus at a second rate, which is faster thanthe first rate. Further, the delay buffer is operable to transfer the audio samples that are stored within the delay buffer to the host at the first rate, after the stored audio samples are transmitted.

Description

[0001] Cross References to Related Applications [0002] This patent application claims priority and benefit to US Patent Application No. 15 / 859,242, filed December 29, 2017, and entitled "VOICE COMMAND PROCESS IN LOWPOWER DEVICES," which is hereby incorporated by reference in its entirety. technical field [0003] According to one or more embodiments, the present disclosure relates generally to audio signal processing, and more particularly, for example, to voice command processing in low power devices. Background technique [0004] Voice-controlled devices such as smart speakers have gained popularity in recent years. These devices typically receive audio through one or more microphones, and then process the received audio input to detect human speech, which may include one or more keywords and voice commands. To save power, many voice-controlled devices enter sleep mode when inactive and wake up after a keyword is detected in audio input to enable further audio input and...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L17/24G10L19/16G06F1/32
CPCG10L2015/223G10L15/22G10L2015/088G06F3/167H04L49/90H04L12/12G10L15/08
Inventor M·J·帕特尔S.伦纳V·杜利甘蒂J·王H·陈
Owner SYNAPTICS INC