Chinese speech recognition model based on activation of the state feedback neural network

This paper proposes a simplified novel speech recognition model, the state feedback neural network activation model (SFNNAM), which is developed based on the characteristics of Chinese speech structure. The model assumes that the current state of speech is only a correction of the last previous state. According to the C-V (Consonant-Vowel) structure of the Chinese language, a speech segmentation method is also implerrented in the SFNNAM model. This model has a definite physical meaning grounded on the structure of the Chinese language and is easily implemented in very large scale integrated circuit (VLSI). In the speech recognition experiment, less calculations were need than in the hidden Markov models (HMM) based algorithm. The recognition rate for Chinese numbers was 93.5% for the first candidate and 99.5% for the first two candidates.