Voice recognition method and device, computer readable storage medium and computer equipment

Abstract

The embodiment of the invention discloses a voice recognition method and device, a computer readable storage medium and computer equipment. The method comprises the steps: carrying out the feature extraction of to-be-recognized voice information, and obtaining a plurality of feature vectors; calculating the sparseness value of each feature vector, wherein the sparseness value is the relative entropy between the distribution of the self-attention score sequence of each feature vector and the uniform distribution of the self-attention score sequence; determining a first feature vector of which the sparseness value is greater than a preset threshold value and a second feature vector of which the sparseness value is not greater than the preset threshold value; determining a target matrix according to the self-attention calculation result of the first feature vector and the second feature vector; and inputting the target matrix and the feature matrix corresponding to the tag sequence into a classification network for classification processing to obtain a recognition result corresponding to the to-be-recognized voice information. Therefore, the deep learning method is adopted, the calculation amount of the self-attention mechanism in the speech recognition process is reduced, and the speech recognition efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a speech recognition method, device, computer-readable storage medium and computer equipment. Background technique [0002] Automatic Speech Recognition (ASR) technology is a technology that allows machines to convert voice signals into corresponding text or commands through the process of recognition and understanding. Speech recognition technology mainly includes three aspects: feature extraction technology, pattern matching criteria and model training technology. [0003] In recent years, automatic speech recognition technology has developed rapidly, and its application has penetrated into various fields of people's lives. Among them, end-to-end (End-to-End, E2E) automatic speech recognition technology is widely favored for its simplified architecture and excellent performance. Transfer machines and attention-based codecs are two popular E2E frameworks. Th...

AI Technical Summary

Problems solved by technology

[0004] However, under the self-attention mechanism, as the length of the input sequence increases, the computational complexity will greatly increase, resulting in low speech recognition efficiency

Images