Wake-up threshold setting method and device, intelligent loudspeaker box and storage medium

A threshold and threshold value technology, applied in the field of smart speakers, storage media, and wake-up threshold settings, can solve the problems of voice interaction equipment incapable of taking into account, low false wake-up rate, poor user experience, etc., and achieve lower wake-up threshold and low false wake-up. rate, the effect of high arousal rate

Inactive Publication Date: 2020-02-14
星络智能科技有限公司
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention mainly provides a wake-up threshold setting method, which can overcome the problem that the existing method for solving the false wake-up of the voice interaction device cannot take into account the high wake-up rate and the low false wake-up rate, resulting in poor user experience.

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
  • Wake-up threshold setting method and device, intelligent loudspeaker box and storage medium
  • Wake-up threshold setting method and device, intelligent loudspeaker box and storage medium
  • Wake-up threshold setting method and device, intelligent loudspeaker box and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] figure 1 It is a flow chart of the wake-up threshold setting method provided by an embodiment of the present invention. The wake-up threshold setting method is applied to a voice interaction device. The voice interaction device can be a smart speaker or a device with a voice interaction function. The voice interaction device has a microphone. The wake-up threshold The setting method includes step S100, step S200, step S300 and step S400.

[0042] Step S100: Whenever a user's voice signal is picked up, perform speech recognition on the user's voice signal, and determine the sound source angle area to which the user's voice signal belongs.

[0043] Specifically, the voice interaction device picks up the user's voice signal through the microphone, and each time the user's voice signal is picked up, it performs voice recognition on the user's voice signal, and determines the sound source angle of the user's voice signal based on the existing sound source localization algori...

Embodiment 2

[0060] figure 2 It is a schematic structural diagram of a wake-up threshold setting device provided by another embodiment of the present invention. The wake-up threshold setting device includes a speech recognition module 100 , a counting module 200 , a probability statistics module 300 and a wake-up threshold setting module 400 .

[0061] The voice recognition module 100 is used to perform voice recognition on the user voice signal whenever the user voice signal is picked up, and determine the sound source angle area to which the user voice signal belongs.

[0062] The counting module 200 is used for counting the number of times of successful speech recognition, and according to the sound source angle area to which the user's sound signal belongs to each time the speech recognition is successful, for each preset sound source angle area, the user's voice signal appears times are counted.

[0063] The probability statistics module 300 is used for judging whether the number of...

Embodiment 3

[0067] image 3 A schematic structural diagram of a smart speaker provided in another embodiment of the present invention, the smart speaker includes a processor 500 and a memory 600, the processor 500 is coupled to the memory 600, and the processor 500 executes instructions during operation to realize the wake-up in any of the above-mentioned embodiments Threshold setting method.

[0068] Wherein, the processor 500 may also be referred to as a CPU (Central Processing Unit, central processing unit). The processor 500 may be an integrated circuit chip with signal processing capabilities. The processor 500 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components . A general-purpose processor may be, but is not limited to, a microprocessor or any conventi...

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

The invention discloses a wake-up threshold setting method and device, an intelligent loudspeaker box and a storage medium. According to the method, the probability that a user sound signal appears ineach preset sound source angle area is counted; and a wake-up threshold of each preset sound source angle area is determined according to a preset wake-up threshold and the probability that the usersound signal appears in each preset sound source angle area. A voice interactive device is generally placed at a fixed location in the home, the user sound signal generally appears in certain fixed angle areas, and the wake-up threshold is adjusted according to the probability that the user sound signal appears in each preset sound source angle area, so that the wake-up threshold of the angle areawith the relatively high probability that the user sound signal appears is low, the wake-up threshold of the angle area with the relatively low probability that the user sound signal appears is high,the wake-up threshold of the user sound signal is reduced, the wake-up threshold of a non-user sound signal is improved, the relatively high wake-up rate and the relatively low false wake-up rate areconsidered, and the user experience is improved.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a wake-up threshold setting method, device, smart speaker and storage medium. Background technique [0002] With the development of science and technology, more and more families begin to use voice interaction devices with voice recognition functions, such as smart speakers. In the home, the voice interaction device usually picks up the sound reflected from the TV or the wall, and these unexpected sounds usually cause the voice interaction device to be woken up by mistake. In order to prevent the voice interactive device from being woken up by mistake, the wake-up threshold is usually adjusted, and the false wake-up rate is reduced by increasing the wake-up threshold, but the wake-up rate is also reduced at the same time, that is, it is difficult for the user to wake up the voice interactive device. Therefore, the existing methods for solving the false wakeup ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L25/78G10L17/22
CPCG10L25/78G10L17/22G10L2025/783G10L2025/786
Inventor 凌华东
Owner 星络智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products