Local voice recognition method based on BP neural network

Abstract

The invention discloses a local voice recognition method based on a BP neural network. The method comprises the following steps that (1) a user inputs voice, command set mapping pairs of operation and voice are set up, and a BP neural network model is obtained; (2) the user inputs voice, forward-propagation is carried out on voice feature parameters input by the user through the BP neural network, an actual output value of a neural network and all expectation values are compared, if one error value is smaller than a preset error value, the step (3) is executed, if all error values are larger than a preset error value X, the step (4) is executed to obtain the name of a neural network output application program, and the application program is started; (4) the error values are subjected to back propagation to be used as input of the BP neural network to correct weights unit one error value is smaller than X; if conditions are stopped, no error value is smaller than X, the training is over. The local voice recognition method has the advantages that the requirement for database memory space is low, the voice recognition speed is high, and accuracy is high.

Description

technical field [0001] The invention relates to a speech recognition method, in particular to a local speech recognition method based on BP neural network. Background technique [0002] Speech recognition is a technology for machines to convert human voice signals into corresponding text or commands through the process of recognition and understanding. Its fundamental purpose is to develop a machine with auditory function, which can directly accept human voice and understand human intent and respond accordingly. As a key field of human-computer interaction, speech recognition has the characteristics of real-time, convenience, and speed, and it also has an increasingly important position in the development of today's science and technology. [0003] Among them, the application of artificial neural network in speech recognition has become the mainstream method of speech recognition at present; however, the speech recognition of existing terminals uses the set database as the ...

AI Technical Summary

Problems solved by technology

[0003] Among them, the application of artificial neural network in speech recognition has become the mainstream method of speech recognition at present; however, the speech recognition of existing terminals uses the set database as the original training set of neural network, and the pre-set in the training set is Some relatively standardized "reference voices". During the recognition process, the user's voice is compared with the standardized "reference voice". Since everyone speaks the same sentence with different voices and speeds, the original training set must store More training samples, slow recognition speed, low precision, and a large storage database is required to store the original training set

[0004] In addition, the voice recognition of existing terminals is basically realized in the following two ways: 1. The database is stored on the network side. In this case, when there is no network, the voice recognition method cannot be used directly.

2. The database exists locally. When the terminal is required to recognize multiple languages ​​and dialects, it will inevitably lead to excessive demand for database storage capacity.

Images