Echo cancellation method and device, computer readable storage medium and electronic device
An echo cancellation and echo technology, applied in speech analysis, instruments, etc., can solve problems affecting speech signal processing performance, etc., and achieve the effect of improving results and performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] This embodiment provides an echo cancellation system, figure 2 is a functional schematic diagram (1) of an echo cancellation system provided according to an embodiment of the present invention, as figure 2 As shown, the echo cancellation system in this embodiment includes:
[0032] The elimination unit 102 includes a preset first neural network model, and the elimination unit is configured to obtain output information according to the sound source signal, the echo estimation information and the first neural network model; the elimination unit 102 is also configured to eliminate the sound according to the output information the echo signal in the source signal;
[0033] Wherein, the sound source signal is an audio signal received by an audio input channel of the terminal, and the echo estimation information is used to indicate an estimated value for estimating the echo signal in the sound source signal;
[0034] The first neural network model is obtained by training ...
Embodiment 2
[0109] This embodiment provides an echo cancellation method, Figure 7 is a flowchart of an echo cancellation method provided according to an embodiment of the present invention, such as Figure 7 As shown, the echo cancellation method in this embodiment includes:
[0110] S202, estimate the echo signal in the sound source signal according to the reference signal and the echo detection information, so as to obtain the echo estimation information; wherein, the sound source signal is the audio signal received by the audio input channel of the terminal, and the reference signal is the audio output of the terminal The audio signal in the channel, the echo detection information is used to indicate the probability of the presence of an echo signal in the sound source signal;
[0111]S204, obtain output information according to the sound source signal, the echo estimation information and the preset first neural network model, and eliminate the echo signal in the sound source signal ...
Embodiment 3
[0179] This embodiment provides a method for training a neural network model, which is used to implement the training of the first neural network model recorded in Embodiment 2, Figure 8 is a flowchart of a training method for a neural network model provided according to an embodiment of the present invention, such as Figure 8 As shown, the training method of the neural network model in this embodiment includes:
[0180] S302, obtain a sample sound source signal; wherein, the sample sound source signal is obtained by superimposing the sample far-end signal and the sample near-end signal, and the sample far-end signal is used to indicate the sample echo signal;
[0181] S304, determine the gain coefficient of the sample sound source signal, and use the gain coefficient as the sample output information;
[0182] S306, establish a first neural network model according to the relationship between the sample sound source signal and the sample output information.
[0183] It shou...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


