Intelligent voice axis cutting method, information data processing terminal and computer program

Abstract

The invention belongs to the technical field of computer software, and discloses an intelligent voice axis cutting method, an information data processing terminal and a computer program. The intelligent voice axis cutting method comprises the following steps: pre-training, namely, carrying out initialization on model parameters through a non-supervision learning algorithm by using abundant data not labelled; and model fine-tuning, namely, learning the model parameters by adopting the traditional neural network learning algorithm and using a small amount of labelled data. According to the technical scheme, effective voice segments are obtained through the windowing framing technology, continuous and stable voice signals are obtained, and the identification errors are reduced; voice signalsare effectively enhanced, the capacity of distinguishing the useless signals is enhanced, the noise interference is eliminated, the errors are reduced, and the voice recognition accuracy rate can be improved by 50%; the problem of background noises can be effectively solved, and the voice recognition accuracy rate is improved to 93%. For acoustic feature extraction, voice feature vector sequencescan be extracted according to voice features similar to that of human beings, background noises and channel distortion are eliminated, and the voice recognition accuracy rate is improved to 94.7%.

Description

technical field [0001] The invention belongs to the technical field of computer software, and in particular relates to an intelligent voice cutting method, an information data processing terminal and a computer program. Background technique [0002] At present, the existing technology commonly used in the industry is as follows : Language is the most convenient and fastest way for human beings to exchange information. With the rapid development of modern network technology, video traffic has gradually become the mainstream of the modern network world, and at the same time, the forms of video transmission tend to be diversified. Video is composed of images and voices. With the support of more and more advanced technologies today, voice recognition technology has become a research hotspot. Speech segmentation is the first pass that speech recognition technology must pass through. Speech segmentation refers to the use of computer programs to automatically segment the basic uni...

AI Technical Summary

Problems solved by technology

[0012] (1) Manual segmentation has higher requirements for talents

[0013] (2) Manual segmentation is inefficient and unable to meet market demand

[0014] (3) The existing voice segmentation technology cannot be accurately segmented when the signal-to-noise ratio is not high

[0016] With the high-performance requirements of the speech recognition system in recent years, it is necessary to intelligently recognize large-scale corpus to meet the video demand of geometric order growth, and the workload of manual segmentation is huge and the efficiency is low.

Using machine automatic segmentation technology can greatly improve the segmentation efficiency, but the traditional automatic segmentation technology cannot meet the existing needs in terms of accuracy. Therefore, it is very important to find a fast and efficient voice automatic segmentation method

Images