An RNN-Based Pre-classification Method for Fast Continuous Mandarin Speech Recognition (0)
| Venue: | IEEE Trans. Speech Audio Processing |
| Citations: | 3 - 0 self |
BibTeX
@ARTICLE{Chen_anrnn-based,
author = {Sin-Horng Chen and Yuan-fu Liao and Song-mao Chiang and Saga Chang},
title = {An RNN-Based Pre-classification Method for Fast Continuous Mandarin Speech Recognition},
journal = {IEEE Trans. Speech Audio Processing},
year = {},
volume = {6},
pages = {86--90}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
A novel RNN-based front-end pre-classification scheme for fast continuous Mandarin speech recognition is proposed in this paper. First, an RNN is employed to discriminate each input frame for the three broad classes of initial, final, and silence. A finite state machine (FSM) is then used to classify the input frame into four states including three stable states of Initial (I), Final (F), and Silence (S), and a Transient (T) state. The decision is made based on examining whether the RNN discriminates well between classes. We then restrict the search space for the three stable states in the following DP search to speed up the recognition process. Efficiency of the proposed scheme was examined by simulations in which we incorporate it with an HMMbased continuous 411 Mandarin base-syllables recognizer. Experimental results showed that it can be used in conjunction with the beam search to greatly reduce the computational complexity of the HMM recognizer while keeping the recognition rate a...
