Voice detection method and system, computer equipment and computer storage medium

A voice detection and algorithm technology, applied in the field of data processing, can solve problems such as low accuracy, unrecognizable voice, low efficiency of voice detection, etc., and achieve the effect of accurate pronunciation detection data and large data volume

Pending Publication Date: 2019-12-03
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the prior art, a single standard voice is used as a reference for comparison, resulting in too many unrecognizable voices, resulting in low efficiency and low accuracy of voice detection

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 detection method and system, computer equipment and computer storage medium
  • Voice detection method and system, computer equipment and computer storage medium
  • Voice detection method and system, computer equipment and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] refer to figure 1 , shows a flow chart of the steps of the speech detection method according to Embodiment 1 of the present invention. It can be understood that the flowchart in this method embodiment is not used to limit the sequence of execution steps. The following takes the computer device 3 as the execution subject to give an exemplary description of the speech detection of a single vocabulary. details as follows.

[0056]Step S100, acquiring pronunciation data to be evaluated of the target user.

[0057] Specifically, the pronunciation data to be evaluated of the target user is collected through a voice input device such as a microphone, and the sound wave waveform is collected, and the main pronunciation features of the pronunciation data to be evaluated are extracted through the common linear predictive coding technology: pronunciation waveform, audio stream, etc.

[0058] Step S102, performing vectorization processing on the pronunciation data to be evaluate...

Embodiment 2

[0084] refer to Figure 4 , shows a flow chart of the steps of the speech detection method according to Embodiment 2 of the present invention. It can be understood that the flowchart in this method embodiment is not used to limit the sequence of execution steps. The following takes the computer device 3 as the execution subject to give an exemplary description of the voice detection of sentences. details as follows.

[0085] In step S200, the voice data of the target user is acquired, and the voice data is divided to obtain a plurality of pronunciation data to be evaluated.

[0086] Specifically, the voice data of the target user is collected through a voice input device such as a microphone, and the sound wave waveform is collected, and the main pronunciation features of the pronunciation data to be evaluated are extracted through the common linear predictive coding technology: pronunciation waveform, audio stream, etc. The voice data contains multiple words, and after seg...

Embodiment 3

[0108] read on Figure 5 , shows a schematic diagram of program modules of Embodiment 3 of the speech detection system of the present invention. In this embodiment, the speech detection system 30 may include or be divided into one or more program modules, and one or more program modules are stored in a storage medium and executed by one or more processors to complete the present invention. Invention, and can realize the above voice detection method. The program module referred to in the embodiment of the present invention refers to a series of computer program instruction segments capable of completing specific functions, which is more suitable for describing the execution process of the voice detection system 30 in the storage medium than the program itself. The following description will specifically introduce the functions of each program module of the present embodiment:

[0109] The obtaining module 300 is used to obtain the pronunciation data to be evaluated of the tar...

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 detection method. The method comprises the following steps: obtaining pronunciation data to be evaluated of a target user; vectorizing the pronunciation data to be evaluated to obtain a pronunciation data matrix to be evaluated; calculating matching values of the pronunciation data matrix to be evaluated and a plurality of preset audio data matrixesaccording to a dynamic time warping algorithm, wherein each preset audio data matrix corresponds to pronunciation data of one vocabulary, and the pronunciation data is standard pronunciation data orwrong pronunciation data; determining the preset audio data matrix with the highest matching value as a target pronunciation data matrix; determining pronunciation data corresponding to the target pronunciation data matrix as target audio data; and generating pronunciation detection data of the pronunciation data to be evaluated according to the target audio data, and pushing the pronunciation detection data to a terminal of the target user. According to the method, matrix calculation is performed by using the dynamic warping algorithm, and optimal matching is performed on the pronunciation data to be evaluated, so that the obtained pronunciation detection data is more accurate.

Description

technical field [0001] The embodiments of the present invention relate to the field of data processing, in particular to a voice detection method, system, computer equipment and computer storage medium. [0002] technical background [0003] With the development of Internet technology, electronic teaching is becoming more and more common, and more and more people learn English through electronic teaching, especially English pronunciation learning. Based on this, many online learning platforms provide voice correction solutions based on voice detection technology, so that users can correct themselves according to the correct pronunciation. Voice detection technology, as a decisive step in the voice correction scheme, is to process and recognize the user's voice signal. However, in the prior art, a single standard voice is used as a reference for comparison, resulting in too many unrecognizable voices, resulting in low efficiency and low accuracy of voice detection. Contents...

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): G10L25/51G10L25/03
CPCG10L25/51G10L25/03
Inventor 卢显锋
Owner PING AN TECH (SHENZHEN) 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