Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Speech signal noise reduction processing method and device

A technology for voice signal and noise reduction processing, applied in voice analysis, instruments, etc., can solve problems such as affecting the quality of user voice calls and inability to produce noise reduction processing effects, and achieve the effect of improving voice call quality and improving noise reduction processing effects.

Active Publication Date: 2015-07-29
中国移动通信集团广西有限公司
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a voice signal noise reduction processing method and device, which are used to solve the problem that in the prior art, when a mobile terminal performs voice signal noise reduction processing based on pre-stored background noise, a good noise reduction processing effect cannot be produced, which affects Issues with the user's voice call quality

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 noise reduction processing method and device
  • Speech signal noise reduction processing method and device
  • Speech signal noise reduction processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0016] Such as figure 1 As shown, it is a schematic flow chart of a method for noise reduction processing of a speech signal proposed in Embodiment 1 of the present invention. The specific processing flow is as follows:

[0017] Step 11: When the mobile terminal is in a voice call, obtain the voice signal generated by the mobile terminal within a specified time period.

[0018] Wherein, obtaining the voice signal generated by the mobile terminal in a predetermined time period may be performed when the noise reduction processing time point is reached, and the predetermined time period may be a time period corresponding to the noise reduction processing time point.

[0019] In the first embodiment of the present invention, the device for performing noise reduction processing on the voice signal may be a mobile terminal, where the voice signal sender mobile terminal may perform noise reduction processing on the voice signal that is generated by the voice signal and to be sent to the call...

Embodiment 2

[0058] Such as figure 2 As shown, it is a schematic diagram of the specific implementation process of the voice signal noise reduction processing method proposed in the second embodiment of the present invention, and the specific processing process is as follows:

[0059] Step 21: When the mobile terminal is in a voice call, if the noise reduction processing time point is reached, the voice signal generated by the mobile terminal in the time period corresponding to the noise reduction processing time point is obtained.

[0060] Step 22: Determine whether the obtained speech signal only contains background noise.

[0061] Step 23: If it is determined that the obtained voice signal contains only background noise, determine the call area where the mobile terminal (ie, the mobile terminal of the voice signal sender) is in the voice call at the noise reduction processing time point.

[0062] Step 24: Update the background noise corresponding to the call area determined in step 23 in the ba...

Embodiment 3

[0069] Correspondingly, the third embodiment of the present invention provides a voice signal noise reduction processing device, the structure of which is as follows image 3 Shown, including:

[0070] The voice signal obtaining unit 31 is configured to obtain a voice signal generated by the mobile terminal within a specified time period when the mobile terminal is in a voice call;

[0071] The background noise determining unit 32 is used to determine whether the voice signal obtained by the voice signal obtaining unit 31 only contains background noise;

[0072] The background noise database updating unit 33 is configured to update the background noise database according to the speech signal obtained by the speech signal obtaining unit 31 when the judgment result of the background noise judging unit 32 is yes;

[0073] The background noise selecting unit 34 is configured to select the background noise for noise reduction processing from the background noises stored in the background n...

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 method and a device for conducting noise reduction on speech signals. The method comprises the steps of obtaining speech signals generated by a mobile terminal in a specified time period when the mobile terminal conducts speech communication; judging whether obtained speech signals only contain background noises or not; if obtained speech signals only contain background noises, updating a background noise library according to obtained speech signals; and if obtained speech signals do not only contain background noises, selecting background noises to be subjected to noise reduction from all background noises stored in the background noise library, and conducting noise reduction on obtained speech signals according to selected background noises. By the aid of the technical scheme, the problems that the speech communication quality of users is affected due to the fact that the good noise reduction effect can not be achieved when the mobile terminal in the prior art conducts noise reduction on speech signals according to background noises stored in advance can be solved.

Description

Technical field [0001] The present invention relates to the technical field of voice communication, in particular to a method and device for noise reduction processing of voice signals. Background technique [0002] With the continuous development of the communications industry, the use of mobile terminals (such as mobile phones) to make voice calls has become an increasingly important way for people to communicate and communicate. Because people are often in a noisy environment, such as users on buses, By the side of a road or in a shopping mall, if a user uses a mobile terminal to make a voice call in such a noisy environment, he will often be disturbed by noise. For example, when user A is located on the side of the road, he will use the mobile terminal to make a voice call with user B , The voice signal received by user B not only includes normal call signals, but also includes noise signals generated when the car passes by. This noise signal can be called background noise. ...

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): G10L21/02
Inventor 刘晓峰梁耿成勇黄中宸李振练
Owner 中国移动通信集团广西有限公司
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
Eureka Blog
Learn More
PatSnap group products