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

Voice wake-up method, device, terminal and storage medium

A voice wake-up, voice technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as user needs that cannot meet wake-up word customization

Active Publication Date: 2017-09-05
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF11 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the existing technology cannot meet the user's demand for customizing the wake-up word

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 wake-up method, device, terminal and storage medium
  • Voice wake-up method, device, terminal and storage medium
  • Voice wake-up method, device, terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] figure 1 This is a flowchart of a voice wake-up method provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of voice wake-up on the smart terminal. The method can be executed by a voice wake-up device, which can be implemented by software and / or hardware. Optionally, the device can be installed in a smart terminal. See figure 1 , The voice wake-up method provided in the first embodiment includes:

[0035] S110. Acquire a wake-up voice used to wake up the smart terminal.

[0036] Wherein, the method for obtaining the wake-up voice can be any method in the prior art that can obtain the wake-up voice. Optionally, it can be obtained by real-time monitoring of surrounding voice information, or it can be obtained after receiving a voice wake-up trigger instruction. voice message.

[0037] Specifically, the voice wake-up trigger instruction can be triggered by pressing one or more physical keys, or can be triggered by clicking a virtual key...

Embodiment 2

[0067] image 3 It is a flowchart of a voice wake-up method provided in the second embodiment of the present invention. This embodiment is an optional solution proposed on the basis of the first embodiment above. See image 3 , The voice wake-up method provided in this embodiment includes:

[0068] S210: Acquire the wake-up word custom trigger instruction and to-be-processed wake-up word data of the smart terminal.

[0069] Among them, the wake word data to be processed is the data to be processed corresponding to the wake word custom trigger instruction. For example, if the wake word custom trigger instruction is to change the wake word, the wake word data to be processed is the text and / or of the new wake word Or voice message.

[0070] Specifically, the wake word custom trigger instruction includes at least deleting the wake word, changing the wake word, and adding the wake word.

[0071] Optionally, the trigger mode of the wake word custom trigger instruction includes clicking a...

Embodiment 3

[0081] Image 6 It is a schematic structural diagram of a voice wake-up device provided in the third embodiment of the present invention. See Image 6 The voice wake-up device provided in this embodiment includes: a voice acquisition module 10, an acoustic feature matching module 20, a voice uploading module 30, and a language feature matching module 40.

[0082] Wherein, the voice acquisition module 10 is used to acquire a wake-up voice for waking up the smart terminal;

[0083] The acoustic feature matching module 20 is configured to use the preset acoustic model of the smart terminal and the preset wake-up word recognition network to analyze the acoustic features of the wake-up speech to obtain the acoustic characteristics of the wake-up speech relative to the preset wake-up words The confidence of

[0084] The voice upload module 30 is configured to upload the wake-up voice to a remote server if the confidence level is within a preset intermediate confidence level;

[0085] The l...

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 voice wake-up method, device, terminal and storage medium, and belongs to the technical field of voice recognition. The method comprises the steps that a wake-up voice used for waking up an intelligent terminal is acquired; a network is recognized by means of a prebuilt acoustic model and a preset wake-up word of the intelligent terminal, analysis is conducted on the acoustic characteristics of the wake-up voice, and the confidence of the acoustic characteristics of the wake-up voice relative to the preset wake-up word is acquired; if the confidence is in the range of preset medium confidence, the wake-up voice is uploaded to a remote server; if the language characteristics acquired by analysis of the wake-up voice by means of a language model in the remote server are matched with the language characteristics of the preset wake-up word, an intelligent terminal wake-up instruction generated by the remote server is received. According to the voice wake-up method, device, terminal and storage medium provided, a custom of the wake-up word is achieved.

Description

Technical field [0001] The embodiments of the present invention relate to the technical field of voice recognition, and in particular to a voice wake-up method, device, terminal and storage medium. Background technique [0002] At present, the most popular smart hardware in the world has voice interaction functions, such as echo, googlehome, etc. Among them, the most mainstream interaction method is to say a wake-up word first. For example, this smart hardware is googlehome, then I must say "hello google", google home can be awakened; then I can start to say my own commands, such as listening to the news, listening Song etc. [0003] In the prior art, one or more fixed wake-up words are generally used to wake up the smart terminal. However, every user has their own personalized needs. For example, I want to change the original voice wake-up word of my mobile phone to my favorite name "Sky Demon". Therefore, the prior art cannot meet user requirements for customizing the wake wor...

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): G10L15/22G10L15/30G10L15/32G10L15/197
CPCG10L15/22G10L15/30G10L15/32G10L15/197G10L2015/223G10L15/08G10L2015/088G10L15/063G10L15/02
Inventor 谢波钱胜孙杨谢延
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com