Voice signal processing method and device

A voice signal processing and voice signal technology, applied in the field of communication, can solve the problem of poor discrimination effect of non-stationary noise, and achieve the effect of improving the accuracy of judgment

Active Publication Date: 2014-01-29
ZTE CORP
View PDF12 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] Aiming at the poor discrimination effect of fast-changing non-stationary noise in the related art, no effective solution has been p

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 signal processing method and device
  • Voice signal processing method and device
  • Voice signal processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0051] In a first manner, it can be determined whether the energy distribution of the speech signal frame is concentrated by calculating the number of speech peaks in the frequency domain of the speech signal frame. When the number of speech peaks in the frequency domain is greater than the first predetermined threshold, it can be determined that the energy distribution of the speech signal frame is not concentrated. Preferably, in the implementation process, the first predetermined threshold may be set to a number greater than 3.

[0052] In the second way, it is also possible to determine whether the energy distribution of the voice signal frame is concentrated by calculating the voice peak energy ratio (Voice Peak Energy Ratio, referred to as VPER) of the voice signal frame. The ratio can refer to the auxiliary voice peak and the main voice peak. energy ratio. When the VPER is less than the second predetermined threshold, it can be determined that the energy distribution o...

Embodiment 2

[0105] In this preferred embodiment, the speech enhancement solution is further described in detail with reference to the accompanying drawings.

[0106] 1. Extraction of speech parameters

[0107] Figure 7 is a schematic diagram of the speech frame parameters in the spectrum domain according to the second embodiment of the present invention, such as Figure 7 As shown, the figure shows the parameters of a frame of speech signal in the spectral domain. Among them, the coordinate of the vertical axis is the frequency spectrum amplitude, the coordinate of the horizontal axis is the sampling point in the frequency domain, and the sampling point interval is described by taking 31.25 Hz as an example. Figure 7 The frequency domain voice peak bandwidth (VPB) of a voice frame is shown in the figure. There are two voice peaks in this figure. The matrix composed of the starting point and the ending point of the frequency band is denoted as VPB1 and VPB2, respectively. They are comp...

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 voice signal processing method and device. The voice signal processing method includes acquiring energy distribution characteristics of a voice signal frame; judging whether the voice signal frame is a noise frame or not according to the energy distribution characteristics. By the voice signal processing method and device, the problem of poor judgment effect on unstable noise fast in changing in the prior art is solved, and judgment accuracy of the noise frame in the voice signal is improved.

Description

technical field [0001] The present invention relates to the field of communications, and in particular, to a voice signal processing method and device. Background technique [0002] At present, people have higher and higher requirements for the voice call function and call quality of mobile terminals. However, the call process in real life is often disturbed by background noise, especially in some public places such as stations, squares, streets, etc. . These non-stationary strong noises have a great impact on the call quality and speech intelligibility, while traditional speech enhancement algorithms usually only have good results for stationary or slowly changing noises, but for fast-changing non-stationary noises The effect of noise suppression is not ideal, and the intelligibility of speech will be lost while suppressing noise. In order to strengthen the tracking and estimation of background noise, the following methods exist in the related art: [0003] First, Donoho...

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): G10L25/51
Inventor 王进军孙焘刘冬梅薛涛王霞姚远
Owner ZTE CORP
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