Unlock instant, AI-driven research and patent intelligence for your innovation.

A voice signal processing method, device and terminal

A voice signal processing and voice signal technology, applied in the direction of voice analysis, advanced technology, climate sustainability, etc., can solve the problems of complex realization, many adjustment parameters, and complicated calculation of overload value, so as to simplify the calculation method and suppress echo Effect

Active Publication Date: 2022-07-12
大众问问(北京)信息科技有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventor found that the existing technology has the following defects: the calculation of the overload value in the existing ES algorithm is relatively complicated, and there are many parameters to be adjusted, and the implementation is relatively complicated

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
  • A voice signal processing method, device and terminal
  • A voice signal processing method, device and terminal
  • A voice signal processing method, device and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] figure 1 It is a flow chart of a speech signal processing method provided in the first embodiment of the present invention. This embodiment can be applied to simplify the determination of the suppression factor in the ES algorithm to perform echo cancellation on the speech signal to be processed. The signal processing apparatus can be implemented by software and / or hardware, and can generally be integrated in a terminal (typically, various types of in-vehicle equipment or terminals such as smart terminal equipment). correspondingly, as figure 1 As shown, the method includes the following operations:

[0033] S110. Acquire the speech signal to be processed and at least two reference signals.

[0034] Wherein, the to-be-processed voice signal may be a voice signal that needs echo cancellation. Exemplarily, a voice command signal (ie a microphone signal) input by a user obtained by the vehicle-mounted terminal through a microphone device or a voice command signal collec...

Embodiment 2

[0048] figure 2It is a flow chart of a voice signal processing method provided in Embodiment 2 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiment. In this embodiment, the calculation of the voice signal to be processed and at least two The cross-correlation parameter of the reference signal and the determination of the initial value of the suppression factor according to the cross-correlation parameter are further specified.

[0049] correspondingly, as figure 2 As shown, the method of this embodiment may include:

[0050] S210. Acquire the speech signal to be processed and at least two reference signals.

[0051] Optionally, the reference signal includes a first reference signal and a second reference signal; the first reference signal is a system audio signal; the second reference signal is a signal obtained by the AEC processing of the to-be-processed voice signal; The cross-correlation parameter is a cross-correlation ...

Embodiment 3

[0091] Figure 3a This is a flowchart of a speech signal processing method provided in Embodiment 3 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiment. In this embodiment, the initial value of the suppression factor and the suppression The overload value of the factor determines the operation process of the inhibitory factor is further specified.

[0092] correspondingly, as Figure 3a As shown, the method of this embodiment may include:

[0093] S310: Acquire the speech signal to be processed and at least two reference signals.

[0094] Optionally, the reference signal includes a first reference signal and a second reference signal; the cross-correlation parameter is a cross-correlation spectrum; the first reference signal is a system audio signal; the second reference signal is the Process the signal obtained by the AEC processing of the speech signal.

[0095] S320. Calculate a first cross-correlation spectrum of the spe...

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 embodiments of the present invention disclose a voice signal processing method, device and terminal. The method includes: acquiring a speech signal to be processed and at least two reference signals; calculating a cross-correlation parameter of the speech signal to be processed and at least two of the reference signals; determining an initial value of a suppression factor according to the cross-correlation parameter; The suppression factor is used to perform echo cancellation on the to-be-processed speech signal; the suppression factor is determined according to the initial value of the suppression factor and the overload value of the suppression factor. By using the technical solution of the present invention, the calculation method of the overload value in the echo cancellation algorithm can be simplified, and the echo can be effectively suppressed.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of voice processing, and in particular, to a voice signal processing method, device, and terminal. Background technique [0002] In the speech signal processing flow, echo cancellation is a commonly used speech signal processing algorithm. In some scenarios, due to the large energy of the echo signal, the AEC (Adaptive Echo Cancellation, adaptive linear echo cancellation) algorithm cannot effectively eliminate the echo, so the ES (Echo Suppression, nonlinear residual echo suppression) algorithm needs to be used to further remove the echo. . [0003] The existing ES algorithm usually obtains the suppression parameters of nonlinear echo cancellation according to the cross-correlation between the speech signal to be processed and the reference signal, and adding overload value and other measures. [0004] In the process of implementing the present invention, the inventor found that the p...

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): G10L21/0216G10L21/0232G10L25/21
CPCG10L21/0216G10L21/0232G10L25/21G10L2021/02082Y02D30/70
Inventor 杨晓霞刘溪
Owner 大众问问(北京)信息科技有限公司