Audio signal processing method and device, equipment and medium

An audio signal processing and sound signal technology, applied in the field of signal processing, can solve the problems of local speech distortion, output speech stuck, nonlinear filter filtering error, etc., to reduce local speech distortion, improve speech quality, and improve user The effect of experience

Pending Publication Date: 2021-03-12
北京融讯科创技术有限公司
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the process of signal processing, the nonlinear echo suppression coefficient is directly determined by using the full-band signal of the microphone receiving signal and the speaker output reference signal, resulting in a large filtering error of the nonlinear filter, and the nonlinear error cannot be completely filtered out. The local voice collected by the microphone is seriously distorted, causing the output voice to freeze, and the user experience is not good

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
  • Audio signal processing method and device, equipment and medium
  • Audio signal processing method and device, equipment and medium
  • Audio signal processing method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] figure 1 It is a flow chart of the audio signal processing method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where the audio signal is processed in real time in the process of voice interaction to suppress noise. The method can be implemented by an audio signal processing device , the apparatus is configured in computer equipment, and specifically may be implemented by software and / or hardware in the computer equipment.

[0052] Such as figure 1 As shown, the audio signal processing method specifically includes:

[0053] S110. Acquire a far-end audio signal and a near-end audio signal, and group the far-end audio signal and the near-end audio signal according to preset frequency band groups to obtain sub-signals of multiple frequency bands.

[0054]Specifically, the far-end sound signal means that among the two parties performing voice interaction, for one of them, the other party's voice signal is the far-end sou...

Embodiment 2

[0068] image 3 It is a schematic structural diagram of an audio signal processing device provided by Embodiment 2 of the present invention. This embodiment of the present invention can be applied to the process of voice interaction to process voice signals in real time and suppress noise. Audio signal processing methods belong to the same inventive concept.

[0069] Such as image 3 As shown, the audio signal processing device in the embodiment of the present invention includes: a signal preprocessing module 210 , an echo prediction module 220 and a noise suppression module 230 .

[0070] Wherein, the signal preprocessing module 210 is used to obtain the far-end sound signal and the near-end sound signal, and group the far-end sound signal and the near-end sound signal according to the preset frequency band grouping respectively to obtain sub-bands of multiple frequency bands. signal; an echo prediction module 220, configured to obtain predicted echo signals corresponding t...

Embodiment 3

[0087] Figure 4 It is a schematic structural diagram of the computer device in Embodiment 3 of the present invention. Figure 4 A block diagram of an exemplary computer device 412 suitable for implementing embodiments of the invention is shown. Figure 4 The computer device 412 shown is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present invention. A computer device can be a device such as a mobile phone, a smart watch, a computer, or a tablet.

[0088] Such as Figure 4 As shown, computer device 412 takes the form of a general-purpose computing device. Components of computer device 412 may include, but are not limited to: one or more processors or processing units 414 , system memory 428 , bus 418 connecting various system components including system memory 428 and processing unit 414 .

[0089] Bus 418 represents one or more of several types of bus structures, including a memory bus or memory controll...

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 discloses an audio signal processing method and device, equipment and a medium. The method comprises steps of obtaining a far-end sound signal and a near-end sound signal, and carrying out the grouping of the far-end sound signal and the near-end sound signal according to a preset frequency band group, and obtaining sub-signals of a plurality of frequency bands; obtaining predicted echo signals corresponding to a plurality of frequency bands based on the sub-signals; and obtaining an initial output signal according to the near-end sound signal and the predictedecho signal, and performing nonlinear signal suppression on the initial output signal to complete an audio signal processing process. According to the method, problems of large error of a filtering result and serious distortion of local voice acquired by a microphone due to full-band filtering of a nonlinear filter in the prior art are solved; linear and non-linear filtering processing can be carried out on the voice signals in a frequency-band-division multi-scale mode, the voice quality is improved, local voice distortion is reduced, and the user experience is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of signal processing, and in particular, to an audio signal processing method, device, device, and medium. Background technique [0002] The echo in the voice interaction system refers to the sound formed by the sound played by the speaker after being reflected by the external environment and entering the microphone. Echoes can interfere with native speech. Due to the existence of echo, the voice interaction system cannot obtain a clean target voice. It is usually necessary to process the voice signal before transmitting the signal to improve user experience. [0003] The processing of the sound signal by the echo suppression device usually includes linear processing and nonlinear processing. First, linear filtering is performed on the signal collected by the microphone and the output reference signal of the loudspeaker through the linear processing module, usually in the form of an ...

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 Applications(China)
IPC IPC(8): G10L21/0208
CPCG10L21/0208G10L2021/02082
Inventor 秦永红李勇强
Owner 北京融讯科创技术有限公司
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