Echo cancellation method and device

Abstract

The present application discloses an echo cancellation method and device. The echo cancellation method includes: updating a parameter of a cloud echo cancellation system by using a first reference signal at a first moment, wherein the first reference signal is a voice synthesizing result after the cloud server responds to a first user instruction; using a target reference signal to perform echo cancellation on a microphone signal through the cloud echo cancellation system at a second moment after the first moment if the microphone signal and the target reference signal uploaded by the client are received. Since cloud echo cancellation can use a more complex echo cancellation algorithm than local and pre-estimate echo cancellation filter parameters, a better echo cancellation effect can beachieved when echo cancellation is performed on the microphone signal.

Description

technical field [0001] The present application relates to the technical field of echo cancellation, and in particular to an echo cancellation method and device. Background technique [0002] In the process of human-computer interaction, after the machine receives user requests (such as voice, text, touch, etc.), it will make corresponding processing according to the user request information, and finally feedback the processing results to the user. Among them, the prompt broadcast is one of the most effective and convenient ways for the machine to feed back information to the user. In the existing various human-computer interaction products, the application of prompting the user through the prompt broadcast is the most widely used, especially in the vehicle environment. , in order to ensure the safety of the driving process, it is particularly important for the user to receive feedback information in the form of hearing during the driving process. [0003] In fact, most of t...

AI Technical Summary

Problems solved by technology

[0004] However, the user interaction voice is recorded by the microphone of the car. At the same time, the microphone will also record the prompt (ie echo signal). In order to ensure the success rate of the interaction, the recorded prompt needs to be recorded from the signal recorded by the microphone. However, the prompts are usually audio synthesized by a text-to-speech (Text To Speech, TTS) synthesis system, and the prompts contain relatively little frequency band information, and compared to the long-term user In terms of interaction, the prompts are short and changeable and sudden. Therefore, the existing echo cancellation technology has a poor echo cancellation effect on the prompts, which will inevitably lead to a decrease in the success rate of the user's secondary interaction.

Images