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

Voice processing method and device, equipment and storage medium

A voice processing and voice data technology, applied in the computer field, can solve problems such as misrecognition and false wake-up, and achieve the effect of improving accuracy and reducing false wake-up.

Active Publication Date: 2019-08-06
ALIBABA GRP HLDG LTD
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The above-mentioned method has a good recall rate. However, some keywords are very similar in pronunciation, such as "Nihao Taobao" and "Nihao Dabao", which are prone to misrecognition, which leads to the problem of false wake-up

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 processing method and device, equipment and storage medium
  • Voice processing method and device, equipment and storage medium
  • Voice processing method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to make the above objects, features and advantages of the present application more obvious and comprehensible, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0055] In the embodiment of the present application, aiming at the problem of false wake-up in voice wake-up, a multi-level verification voice processing method is proposed, and the parsed recognition keywords can be multi-level verified by multi-dimensional confidence classifiers, thereby outputting Through the final keyword of multi-level verification, the accuracy of keyword recognition is improved and the problem of false awakening is reduced. Wherein, a keyword (Keyword) refers to a word representing the main meaning of the voice data, and the keyword can be a single character or a word, which can be recognized from the voice data.

[0056] like figure 1 In the speech processing schematic diagram s...

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 provides a voice processing method and device, equipment and a storage medium, and aims to reduce the problem of false awakening. The method comprises the following steps: analyzing voice data to obtain one or more recognition keywords and corresponding confidence information; performing multi-level confidence verification on the one or more recognition keywords byadopting a plurality of confidence classifiers; and outputting the final keyword passing the multi-level verification. Through multi-level confidence verification, the accuracy of keyword recognitioncan be effectively improved, and the problem of false awakening is reduced.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a voice processing method and device, an electronic device and a storage medium. Background technique [0002] With the development of terminal technology, voice wake-up technology has been widely applied, that is, users can wake up services such as applications they need by voice in the terminal, such as querying routes by voice, waking up various applications by voice, and so on. [0003] At present, voice wake-up usually uses a limited-scale deep neural network (Deep Neural Network, DNN) model to build a small automatic speech recognition (Automatic Speech Recognition, ASR) system, and the keyword recognition is performed through the ASR system, and ; At the same time, some systems train a confidence classifier for custom keywords to optimize. [0004] This solution is similar to the voice wake-up technology based on DNN acoustic model (AM), and the voice wake-up ...

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): G10L15/02G10L15/14G10L15/22G10L15/26
CPCG10L15/22G10L15/26G10L15/063G10L15/14G10L15/02G10L15/1822G10L25/24G10L2015/223G10L2015/0631G10L2015/025
Inventor 姚海涛
Owner ALIBABA GRP HLDG 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