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

Speech signal detection method, computer storage medium and related equipment

A voice signal and detection method technology, applied in voice analysis, voice recognition, instruments, etc., can solve the problem of low reliability of detection results, improve product service quality, improve reliability and effectiveness, and reduce false trigger rate Effect

Active Publication Date: 2022-05-13
GUANGZHOU SHIYUAN ELECTRONICS CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a voice signal detection method, a computer storage medium and related equipment to at least solve the technical problem in the related art that the threshold value is used as the judgment basis for voice signal detection and the reliability of the detection result is not high

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
  • Speech signal detection method, computer storage medium and related equipment
  • Speech signal detection method, computer storage medium and related equipment
  • Speech signal detection method, computer storage medium and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] According to an embodiment of the present application, a voice signal detection method is provided, the method is applied to a voice interactive product, and can be deployed on an audio signal processing platform of the product.

[0049] Combine below figure 1 The video detection method provided in the embodiment of the present application is introduced in detail. Such as figure 1 As shown, the method includes the following steps:

[0050] Step S102, obtaining the current audio signal collected at the current moment and a plurality of historical audio signals collected at the historical moment;

[0051] Considering the temporal correlation of voice signals, in order to improve the reliability of voice signal detection, when detecting voice signals, it is not only necessary to obtain the current audio signal collected at the current moment, but also to obtain the historical audio signals collected at historical moments. audio signal.

[0052] The greater the number o...

Embodiment 2

[0061] Such as figure 1 As shown, the method includes the following steps:

[0062] Step S102, obtaining the current audio signal collected at the current moment and a plurality of historical audio signals collected at the historical moment;

[0063] Step S104, using Bayesian filtering to process the current audio signal and multiple historical audio signals to obtain the posterior probability of the current audio signal, wherein the posterior probability includes: the posterior probability that the current audio signal contains a speech signal, and the current the posterior probability that the audio signal does not contain a speech signal;

[0064] Specifically, the specific implementation of Bayesian filtering is as follows: the current audio signal and multiple historical audio signals are modeled to obtain the probability distribution of the current audio signal, wherein the probability distribution includes: the probability distribution that the current audio signal con...

Embodiment 3

[0100] According to an embodiment of the present application, a voice signal detection method is provided, the method is applied to a voice interactive product, and can be deployed on an audio signal processing platform of the product. Such as image 3 As shown, the method includes the following steps:

[0101] Step S302, obtaining the current audio signal collected at the current moment and a plurality of historical audio signals collected at the historical moment;

[0102] Step S304, modeling the current audio signal and multiple historical audio signals to obtain the probability distribution of the current audio signal, wherein the probability distribution includes: the probability distribution that the current audio signal contains a speech signal, and the probability distribution that the current audio signal does not contain a speech signal Probability distributions;

[0103] In this embodiment, the specific implementation of modeling is as follows: process the current...

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 application discloses a speech signal detection method, a computer storage medium and related equipment, which belong to the technical field of speech recognition. Wherein, the method includes: obtaining the current audio signal collected at the current moment and a plurality of historical audio signals collected at the historical moment; using Bayesian filtering to process the current audio signal and the plurality of historical audio signals to obtain the current audio signal The posterior probability, wherein the posterior probability includes: the posterior probability that the current audio signal contains a speech signal, and the posterior probability that the current audio signal does not contain a speech signal; based on the posterior probability of the current audio signal and a preset threshold value, A detection result of the current audio signal is obtained, wherein the detection result is used to characterize the probability that the current audio signal contains a speech signal. Therefore, the embodiment of the present application can improve the reliability and validity of the detection result, improve the detection quality of the audio signal, and effectively reduce the false trigger rate of the speech recognition system.

Description

technical field [0001] The present application relates to the field of voice recognition, in particular, to a voice signal detection method, a computer storage medium and related equipment. Background technique [0002] In voice interactive products, the collected voice signal can be recognized and analyzed through the voice recognition system. However, in the application scenario of far-field voice recognition, the voice signal at the receiving end is weak, and the strong noise in the environment will significantly reduce the audio frequency. The detection quality of the signal can easily cause false triggering of the recognition system. [0003] In the environment of strong noise and weak signal, the signal detection method based on the statistical characteristics of the received signal can be used at present. This method uses the threshold value as the basis for judgment, and can only use the data of the current frame for judgment, resulting in the reliability of the dete...

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 Patents(China)
IPC IPC(8): G10L25/78G10L25/84G10L15/20G10L15/22
CPCG10L25/78G10L25/84G10L15/20G10L15/22G10L2025/783G10L2015/223
Inventor 王亮亮
Owner GUANGZHOU SHIYUAN ELECTRONICS CO 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