Intelligent speech recognition method and device and computer readable storage medium

Abstract

The invention relates to an artificial intelligence technology, and discloses an intelligent speech recognition method. The intelligent speech recognition method comprises the steps that a speech set and a text set are received, and pre-processing operation is performed on the speech set and the text set; an acoustic feature set is obtained by extracting acoustic features in the pre-processed speech set, a phoneme set is constructed based on the acoustic feature set, and a state relationship is established between the pre-processed text set and the phoneme set; an acoustic model is constructed based on naive Bayes and LSTM algorithms, the phoneme set and the pre-processed text set are input to the acoustic model for training until the training value of the acoustic model is less than a preset threshold value; and user speech is received, after the user speech is recognized by the acoustic model, the user speech is converted into a text format, and the text result is output. The invention further provides an intelligent speech recognition device and a computer readable storage medium. The intelligent speech recognition method can convert the user speech into text for output.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device and computer-readable storage medium for intelligently performing speech recognition based on speech input. Background technique [0002] Speech recognition methods can enable smoother communication between people and machines, and allow machines to literally understand what users are saying, which is the basis of natural human-computer interaction. Speech recognition methods are now widely used, and the demand for speech recognition is also increasing. However, the current speech recognition methods require a large amount of speech data and the support of text corresponding to these speeches, and most speech recognition methods are inefficient, and the effect needs to be improved. Contents of the invention [0003] The present invention provides an intelligent speech recognition method, device and computer-readable storage medium, the ...

AI Technical Summary

Problems solved by technology

However, the current speech recognition methods require a large amount of speech data and the text corresponding to these speech supports, and most of the speech recognition methods are inefficient, and the effect needs to be improved

Images