Method for detecting movable voice endpoint

Abstract

The invention relates to a detecting method of active voice end, which comprises the following steps including 1) receiving continuous voice and obtaining frame from the continuous voice, 2) calculating the energies of the frame obtained in step 1) and obtaining energy threshold value according to the energies, 3) respectively calculating the zero-crossing rate of the frame obtained in step 1) and obtaining the zero-crossing rate threshold value according to the zero-crossing rates, 4) using linear regression deductive method to judge whether each frame is active voice or inactive voice by taking the energies obtained in step 2) and the zero-crossing rates obtained in step 3) as input parameter of the linear regression deductive method and 5) obtaining active voice starting point and active voice end point in the active voices or inactive voices of the step 4) according to the energy threshold value and the zero-crossing rate threshold value. The invention increases the judging accuracy rate of the active voice starting point and active voice end point, and also improves the correctness rate of voice identification.

Description

technical field [0001] The invention relates to a voice recognition detection method, in particular to a detection method for active voice endpoints used to improve the correct rate of active voice recognition. Background technique [0002] After the original voice analog signal is digitized, it can be directly used for identification, but due to the large amount of data, long processing time, and poor efficiency, it is impossible to store all the original voice as a standard voice reference sample, so it must be According to the characteristics of the digitized voice signal, feature acquisition is performed to obtain appropriate feature parameters for comparison and identification. Moreover, obtaining representative feature parameters for the voice signal can reduce the amount of data and increase efficiency. Generally, the flow of Chinese speech recognition for non-specific speakers is shown in Figure 1, which includes the following steps: [0003] Step 1) Voice signal i...

AI Technical Summary

Problems solved by technology

[0007] Whether the current input signal sound frame is an active voice (activevoice, meaning the voice of the conversation in the conversation) paragraph or an inactive voice (inactive voice, meaning the silence or background noise that pauses in the conversation) is determined by the currently used judgment method. Misjudgments still occur

If a misjudgment occurs, when the feature parameters are acquired, because the target voice includes active voice and inactive voice, the accuracy of voice recognition will decrease

Images