Voice quality assessment method and device based on voice activation detection

A voice activation detection and voice quality technology, applied in voice analysis, instruments, etc., can solve problems such as inability to quantitatively control input voice quality, and inability to evaluate voice quality.

Inactive Publication Date: 2018-05-08
SPEAKIN TECH CO LTD
View PDF9 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a voice quality assessment method and device based on voice activation detection, which solves the problem of not being able to evaluate the quality of voic

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 quality assessment method and device based on voice activation detection
  • Voice quality assessment method and device based on voice activation detection
  • Voice quality assessment method and device based on voice activation detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The embodiment of the present invention provides a voice quality assessment method and device based on voice activation detection, which solves the problem that only combining voice activation detection, in addition to distinguishing voice and noise, cannot evaluate the quality of voice, resulting in inability to quantify Technical issues controlling the quality of recorded speech.

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0064] see figure 1 , the embodiment of the present invention provide...

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 quality assessment method and a device based on voice activation detection. Framing processing is performed on an input sample audio file and a short-time stationary audio signal is acquired. The voice activation detection is performed on the short-time stationary audio signal and a frame corresponding to the short-time stationary audio signal is determined to be a voice frame or a non-voice frame. A preset frame number is taken as a step length so as to carry out voice quality detection on fragment audio files of a sample audio file, the fragment audio files with qualified quality are reserved and the unqualified fragment audio files are abandoned. When only a voice activation detection mode is combined, voices and noises are distinguished, but voice qualitycan not be assessed so that input voice quality can not be quantitatively controlled. In the invention, the above technical problem is solved.

Description

technical field [0001] The invention relates to the field of voice detection, in particular to a voice quality evaluation method and device based on voice activation detection. Background technique [0002] The advent of the big data era has brought massive multimedia information. In the audio field, people have higher and higher requirements for live recorded audio, hoping to hear clearer and more complete audio. [0003] Most of the current conventional recording methods are to collect sound source signals through microphones (digital microphones or analog microphones), and record audio directly on the computer or mobile terminal with recording software. However, in actual voice conversations, the effective voice duration generally does not exceed 40% of the total duration, which includes a large number of meaningless segments, such as silence, noise, or pauses. Most of the existing technologies only combine the VAD (Voice Activty Detection, Voice Activation Detection) al...

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): G10L25/03G10L25/60G10L25/84
CPCG10L25/03G10L25/60G10L25/84
Inventor 晏青
Owner SPEAKIN 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

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