Speech recognition method and system

Abstract

The invention belongs to the speech recognition technical filed and relates to a speech recognition method and system. The method includes the following steps that: speech signals are acquired; analog-digital conversion is performed on the speech signals, so that corresponding speech digital signals can be generated; preprocessing is performed on the speech digital signals, and speech feature parameters are extracted according to corresponding preprocessing results, and a time sequence of extracting the speech feature parameters is utilized to construct a corresponding feature sequence; the speech feature parameters are matched with speech models in a template library, and the feature sequence is decoded according to a search algorithm, and therefore, a corresponding recognition result can be generated. According to the speech recognition method and system of the invention, time-domain GFCC (gammatone frequency cepstrum coefficient) features are extracted to replace frequency-domain MFCC (mel frequency cepstrum coefficient) features, and DCT conversion is adopted, and therefore, computation quantity can be reduced, and computation speed and robustness can be improved; and the mechanism of weighted finite state transformation is adopted to construct a decoding model, and smoothing and compression processing of the model is additionally adopted, and therefore, decoding speed can be increased.

Description

technical field [0001] The invention belongs to the technical field of voice recognition, in particular to an embedded voice recognition method and system. Background technique [0002] Speech recognition is a key technology for realizing human-computer interaction by using machines to recognize user voice commands, which can significantly improve the way of human-computer interaction so that users can complete more tasks while speaking commands. Speech recognition is realized by a speech recognition engine trained online or offline. The speech recognition process can generally be divided into a training phase and a recognition phase. In the training phase, an acoustic model (AM) and a vocabulary (lexicon) are statistically obtained from the training data according to the mathematical model on which the speech recognition engine is based. In the recognition stage, the speech recognition engine uses the acoustic model and vocabulary to process the input speech to obtain spe...

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a method and system for speech recognition, which is used to solve the problems of poor adaptability, strong dependence on the environment and uncertainty of endpoint detection in existing speech recognition methods, resulting in The problem of low decoding efficiency

Images