Voice boundary detection method and system assisted by voice portrait

A boundary detection and speech detection technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as slow speech speed and low success rate of speech recognition, and achieve the effect of improving the success rate and experience

Pending Publication Date: 2020-07-10
BEIJING UNISOUND INFORMATION TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the general speech recognition process, for example, in the scenario where a child or a user who speaks slowly and does not express himself fluently interacts with the device, the user starts to perform speech recognition before the expression is completed, resulting in a low success rate of speech recognition

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 boundary detection method and system assisted by voice portrait
  • Voice boundary detection method and system assisted by voice portrait
  • Voice boundary detection method and system assisted by voice portrait

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0063] This embodiment provides a voice boundary detection method assisted by a sound image, such as figure 1 shown, including the following steps:

[0064] S1: Receive the voice information of the target user.

[0065] S2: Extracting audio image information in the received audio information. In this embodiment, the voice image information extracted according to the user's voice includes age, speech speed, and expression fluency information, where the speech speed is divided into fast, medium, and slow, and the expression fluency is divided into good, medium, and low.

[0066]S3: Based on the speech recognition scoring model, identify and score all the target item...

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 provides a voice boundary detection method assisted by a voice portrait. The method comprises the following steps: S1, receiving voice information of a target user; S2, extracting voiceportrait information in the received voice information; S3, based on a voice recognition scoring model, recognizing and scoring all target items in the extracted voice portrait information one by one,and obtaining a comprehensive score; and S4, according to the comprehensive scoring result, obtaining a voice boundary detection duration related to the target user. According to the voice boundary detection method and device assisted by the voice portrait, the voice boundary detection duration matched with different users can be determined according to the different users, so that the voice recognition success rate is increased, and the user experience is improved.

Description

technical field [0001] The invention relates to the technical field of voice boundary detection, in particular to a voice boundary detection method assisted by a sound image. Background technique [0002] Voice boundary detection is voice activity detection (Voice Activity Detection, vad), also known as voice endpoint detection. In the general speech recognition process, for example, in the scenario where a child or a user who speaks slowly and has poor language expression interacts with the device, the user starts to perform speech recognition before the expression is completed, resulting in a low success rate of speech recognition. At this time, it is necessary to detect the duration of the speech boundary detection, so as to improve the success rate of speech recognition. Contents of the invention [0003] In order to overcome the above problems, the present invention provides a voice boundary detection method assisted by a voice image, which specifically includes the ...

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): G10L25/78G10L25/87G10L15/05G10L15/06
CPCG10L25/78G10L25/87G10L15/05G10L15/063
Inventor 高扬
Owner BEIJING UNISOUND INFORMATION TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap