Neural network voice recognition method and system for home spoken language environment

Abstract

The invention discloses a neural network voice recognition method and system for a home spoken language environment. The method comprises the steps of building a model: adding a long-term and short-term memory network into a deep neural network, and building a combined neural network DNN-LSTM model, preprocessing the acquired voice data set to obtain a feature vector set, taking the feature vectorset as the input of the DNN-LSTM model for iterative training, and training to an optimal acoustic model, respectively obtaining a Chinese output probability vector set and an English output probability vector set from an input voice signal of an unknown language and the trained DNN-LSTM model, and performing language matching according to the Chinese output probability vector set and the Englishoutput probability vector set, and outputting a judgment result. The method can quickly and accurately identify the content of the speaker in the home scene, and can be widely applied to the actual home scene.

Description

technical field [0001] The invention belongs to the technical field of intelligent recognition, and in particular relates to a neural network speech recognition method and system for home spoken language environment. Background technique [0002] The key object of speech recognition research is speech, which converts speech signals into information that can be recognized by computers, so as to recognize the speaker's speech commands and text content. Speech recognition methods can basically be divided into three types: three methods based on linguistics and acoustics, model matching and neural networks. Although the first method appeared earlier, due to the limitations of its complex model, it has not yet reached a more practical stage; the second method is mostly used in the hidden Markov model, which can be used to label the probability model of the problem, And it shows that the model randomly generates observation sequences, which greatly improves the speech recognition...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a neural network speech recognition method oriented to the home spoken language environment, which can solve the problems of low speech recognition rate and poor recognition efficiency. The present invention also provides a home-oriented Neural Network Speech Recognition System in Spoken Language Environment

Images