Echo elimination method based on deep learning

A technology of echo cancellation and deep learning, which is applied in neural learning methods, sound-generating devices, two-way sound reinforcement telephone systems, etc., and can solve problems such as poor echo cancellation effect and the need for post-filters

CN109841206AActive Publication Date: 2019-06-04ELEVOC TECH CO LTD
7 Cites 36 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2019-06-04

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an echo elimination method based on deep learning, an echo elimination device based on deep learning, electronic equipment and storage medium, and belongs to the technical field of a computer. The method comprises the following steps of extracting acoustic features from received microphone signals, wherein the microphone signals comprise near-end signals and remote-end signals; performing iterative operation on the acoustic features in a pretrained recursive neural network model with long short-term memory; calculating a ratio membrane of the acoustic features; using the ratio membrane for shielding the acoustic features; and synthesizing the shielded acoustic features with the phase of the microphone signals to obtain near end signals subjected to echo elimination.The echo elimination method based on deep learning and the echo elimination device based on deep learning can realize the echo elimination under the conditions of the background noise, double talking, nonlinear distortion and the like; the echo elimination effect is greatly improved; the application scenes are greatly increased; the use of a post-filter is not needed; the electronic equipment iseffectively simplified; and the electronic equipment cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical field

[0001] The present disclosure relates to the field of computer application technology, and in particular to an echo cancellation method, device, electronic equipment, and storage medium based on deep learning. Background technique

[0002] In a communication system, when a speaker and a microphone are coupled, the microphone will pick up the signal from the speaker and its reverberation, thereby generating echo. For example, conference calls, hands-free phones and mobile communications all suffer from echo.

[0003] Echo cancellation faces many problems, such as dual talk, background noise, and nonlinear distortion. First of all, dual talk is a typical way of dialogue in communication systems, and speakers at both ends sometimes speak at the same time. However, near-end speech signals will seriously affect the convergence of the adaptive algorithm and may cause them to diverge. In addition, the signal received at the microphone contains not only echo and near-end...

Examples

Embodiment Construction

[0060] Here, an exemplary embodiment will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present invention. On the contrary, they are only examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0061] figure 1 It is a flow chart showing a method for echo cancellation based on deep learning according to an exemplary embodiment. This deep learning-based echo cancellation method can be used in electronic devices such as smart phones and computers. Such as figure 1 As shown, the deep learning-based echo cancellation method may include step S110, step S120, step S130, ...