Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speech wake-up method and device

A voice wake-up and voice segment technology, applied in speech analysis, voice recognition, instruments, etc., can solve the problem of high false wake-up rate, reduce the false wake-up rate and improve the wake-up accuracy rate

Pending Publication Date: 2020-11-03
SOUNDAI TECH CO LTD
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, the interaction is usually achieved through voice, such as smart speakers, mobile phones, tablets, etc., but in the process of waking it up by the user, the problem of high false wakeup rate often occurs

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
  • Speech wake-up method and device
  • Speech wake-up method and device
  • Speech wake-up method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] In order to solve the technical problem of high false wakeup rate in the prior art, an embodiment of the present disclosure provides a voice wakeup method. Such as figure 1As shown, the voice wake-up method mainly includes the following steps S11 to S15.

[0059] Step S11: Acquire a voice signal.

[0060] Wherein, the voice signal includes a wake-up word. For example, the wake word could be Hello Teng!

[0061] Specifically, the voice signal can be acquired through a smart device, such as a smart phone, a tablet computer or a desktop computer; the voice signal comes from a user.

[0062] Step S12: Input the speech signal into a first model, and output the first posterior probability of each frame of phoneme in the speech signal through the first model.

[0063] Wherein, the first model may be an acoustic model.

[0064] Specifically, a batch of voice signals can be obtained and marked, for example, if the voice signal contains a preset keyword (for example, device...

Embodiment 2

[0100] In order to solve the technical problem of high false wakeup rate in the prior art, an embodiment of the present disclosure provides a voice wakeup device. The device can execute the steps in the embodiment of the voice wake-up method described in the first embodiment above. Such as figure 2 As shown, the device mainly includes: a voice acquisition module 21, a first posterior probability determination module 22, a wake-up speech segment determination module 23, a second posterior probability determination module 24 and a wake-up module 25; wherein,

[0101] Voice acquiring module 21 is used for acquiring voice signal;

[0102] The first posterior probability determining module 22 is used to input the speech signal into a first model, and output the first posterior probability of each frame of phoneme in the speech signal through the first model;

[0103] The wake-up speech segment determination module 23 is used to use the speech signal corresponding to the phoneme ...

Embodiment 3

[0115] Refer below image 3 , which shows a schematic structural diagram of an electronic device 300 suitable for implementing the embodiments of the present disclosure. The terminal equipment in the embodiment of the present disclosure may include but not limited to such as mobile phone, notebook computer, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle terminal (such as mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers and the like. image 3 The illustrated electronic device is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present disclosure.

[0116] Such as image 3 As shown, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which may be loaded into a random access memory (RAM) accordin...

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 speech wake-up method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring a speech signal; inputtingthe speech signal into a first model, and outputting a first posterior probability of each frame of phoneme in the speech signal through the first model; taking a speech signal corresponding to the phoneme of which the first posterior probability meets a first wake-up condition as a wake-up speech segment; inputting the spectrogram and the posterior probability graph of the wake-up voice segment into a second model, and outputting a second posterior probability of each frame of phoneme in the wake-up speech segment through the second model; if the second posterior probability satisfies a second wake-up condition, performing a wake-up operation. According to the embodiment of the invention, through secondary wake-up confirmation, the false wake-up rate can be reduced, and the wake-up accuracy is improved.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular to a voice wake-up method, device and computer-readable storage medium. Background technique [0002] With the rapid development of artificial intelligence, smart devices are becoming more and more popular among the public, and there are more and more evaluations of smart devices (such as smart speakers) from various manufacturers. The primary experience of smart devices is no longer enough to satisfy the majority. Users, which also brings the demand for smart device optimization. [0003] In the prior art, interaction is usually achieved through voice, such as smart speakers, mobile phones, tablets, etc., but in the process of waking up by the user, the problem of high false wakeup rate often occurs. Contents of the invention [0004] This Summary is provided to introduce a simplified form of concepts that are described in detail later in the Detaile...

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): G10L15/22
CPCG10L15/22
Inventor 杨晓帆冯大航陈孝良
Owner SOUNDAI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products