Double track based audio data calibration method and multi-people voice talking system thererof

Abstract

The present invention discloses a method based on dual-track audio data demarcation, and the method includes the steps as follows. After audio data in at least one channel is obtained, the virtual position of each-channel audio data is decided by the number of audio data channels; in any channel of audio data, according to the sound volume of audio data in the current channel and the virtual position of audio data in the current channel, and being corresponding to audio data in the current channel, the proportions for sound volume of left and right sound tracks are adjusted till the operationon audio data in each channel is completed. The present invention also discloses a multi-person voice talk system based on dual-track audio data demarcation. The adoption of the method and the systemcan not only realize the demarcation and the differentiation of multi-channel audio data, but also greatly improve the recognizing ability of each-channel audio data of multi-channel audio data.

Description

technical field [0001] The invention relates to an audio data calibration technology, in particular to a dual-channel audio data calibration method and a multi-person voice communication system. Background technique [0002] People can only hear the size of the sound through one ear, which is the intensity or volume of the sound. Since the distance and direction of the sound source cannot be determined by the size of the sound, the source of the sound cannot be located through one ear. The principle of locating the sound source by the human ear is realized based on the two ears of the human being. Specifically, it is based on the fact that the two ears can distinguish the time difference of the sound and the difference in the intensity of the sound. These two characteristics are used to accurately locate the source of the sound. For example, the sound coming from the left first arrives at the left ear of the person, and then arrives at the right ear. There is a time differ...

AI Technical Summary

Problems solved by technology

However, when the video image does not exist / is not synchronized, the receiver is not familiar with the tone of the sender, or the tone of multiple senders is similar, the receiver can easily confuse the sender or cannot distinguish the identity of the sender

That is to say, it is impossible to calibrate and distinguish multiple channels of audio data in the system by using the existing technology, resulting in a low ability to identify each channel of audio data of the multiple channels of audio data

Images