Self-adaptive voice endpoint detection method and detection circuit

An endpoint detection and self-adaptive technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as poor adaptation, system power loss, low signal-to-noise ratio, etc., to improve adaptability and robustness, avoid The effect of misjudgment

Active Publication Date: 2021-10-01
成都启英泰伦科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology allows us to selectively process signals based on their noise level rather than just its power spectral density (PSF). It also improves upon previous methods by providing flexibility with regards to both temporal and spatial dimensions. Additionally, it prevents errors from being detected due to incorrect loudspeaker settings. Overall, this innovation enhances how we are able to handle complicated situations better while still maintaining good performance over different types of sounds.

Problems solved by technology

Technological Problem addressed in this patents relates to improving speech recognizing systems' efficiency and responsiveness during periods where noisy signals occur frequently while maintaining their reliance over irrelevant background sounds like conversations between people who speak different languages. Current approaches have limitations such as lacked flexibility, limited range of sound intensity levels, and insufficient sensitivity at very small acoustic pressures caused by factors like interference from other sources.

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
  • Self-adaptive voice endpoint detection method and detection circuit
  • Self-adaptive voice endpoint detection method and detection circuit
  • Self-adaptive voice endpoint detection method and detection circuit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Specific embodiments of the present invention will be further described in detail below.

[0058] A kind of self-adaptive speech endpoint detection method of the present invention, it comprises the following steps:

[0059] Step S0. Carry out time-domain signal segmentation to the input voice signal, and divide the input voice signal into a single-frame time-domain signal according to the frame length and frame shift set; a specific method of segmentation is as follows figure 2 as shown,

[0060] The following steps S1-1 to S2-7 are carried out frame by frame;

[0061] Step S1-1. Use the square value of the single-frame time-domain signal as the time-domain energy signal ET(k), and calculate the time-domain basic background energy Eback(k);

[0062] The specific calculation formula of time domain energy signal ET(k) is: ;

[0063] Wherein N is the total number of points in the single-frame signal, m is the sequence number of the single-frame time-domain signal, n is th

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 self-adaptive voice endpoint detection method. The method comprises the following steps: segmenting an input voice signal into a single-frame time domain signal; calculating time domain basic background energy, time domain maximum background energy, time domain final background energy and time domain voice existence probability; performing windowing processing and discrete Fourier transform on the single-frame time domain signal, and calculating the frequency domain voice existence probability; calculating an effective judgment probability according to the time domain voice existence probability, the frequency domain voice existence probability and the signal-to-noise ratio; and judging whether effective voice exists or not according to the effective judgment probability Pfinal. According to the method, the signal-to-noise ratio is used as a judgment condition for selecting time domain processing or frequency domain processing to judge whether voice exists or not, the problem that the requirement for high adaptability to a complex environment is difficult to meet in the prior art is solved, and the adaptability and robustness of an algorithm to the environment are improved.

Description

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

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
Owner 成都启英泰伦科技有限公司
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