Voice wake-up method, device and equipment

A voice wake-up and device technology, applied in voice analysis, voice recognition, instruments, etc., can solve the problems of slow decoding speed and less text, and achieve the effect of improving wake-up efficiency

Pending Publication Date: 2021-08-31
BEIJING YOUZHUJU NETWORK TECH CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the current wake-up schemes are all judged at the voice frame level. For example, the input voice has 100 frames, and the actual text is very little. Through the above-mentioned wake-up scheme, the decoding path with a length of 100 will be searched to determine whether to recall , resulting in slower decoding

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 and equipment
  • Voice wake-up method, device and equipment
  • Voice wake-up method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the above objects, features and advantages of the present application more obvious and understandable, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It can be understood that the specific embodiments described here are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only parts relevant to the present application are shown in the drawings, not all structures.

[0029] In order to facilitate the understanding of the technical solutions provided by the embodiments of the present application, the technical terms involved in the present application will be described first.

[0030] Keyword spotting (KWS) refers to the real-time detection of speaker-specific segments in a continuous speech stream. The purpose of voice wake-up ...

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 embodiment of the invention discloses a voice wake-up method, device and equipment. The method comprises the steps of for an acquired to-be-processed voice signal, acquiring to-be-processed voice features from the to-be-processed voice signal, and coding the to-be-processed voice features to obtain acoustic coding representations; after the acoustic coding representations corresponding to the to-be-processed voice signal are obtained, carrying out integration according to the acoustic coding representations and the weights corresponding to the acoustic coding representations, and then obtaining a character sequence included in the to-be-processed voice signal according to the integrated acoustic coding representations; and after the character sequence is obtained, determining whether to wake up the equipment or not according to the character sequence and the keyword. That is, possible characters are acquired from the to-be-processed voice signal, and then whether to wake up or not is judged based on the character level instead of a voice frame, so that the wake-up efficiency is improved.

Description

technical field [0001] The present application relates to the technical field of computer processing, and in particular to a voice wake-up method, device and equipment. Background technique [0002] Voice wake-up is a very important technology in the voice field at present, and it is more deployed on hardware, which helps users complete some tasks after receiving voice commands. Traditional wake-up methods usually include an acoustic model for speech recognition and finite state transducers (Finite State Transducers, FST) including keywords and path clipping, and judge whether to wake up based on confidence. [0003] However, the current wake-up schemes are all judged at the voice frame level. For example, the input voice has 100 frames, and the actual text is very little. Through the above-mentioned wake-up scheme, the decoding path with a length of 100 will be searched to determine whether to recall , resulting in slower decoding. Contents of the invention [0004] In ...

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): G10L15/22G10L15/02G10L15/26
CPCG10L15/22G10L15/02G10L15/26G10L2015/223
Inventor 梁镇麟董林昊蔡猛马泽君
Owner BEIJING YOUZHUJU NETWORK TECH CO LTD
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