By Topic

A modular RNN-based method for continuous Mandarin speech recognition

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Yuan-Fu Liao ; Dept. of Commun. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan ; Sin-Horng Chen

A new modular recurrent neural network (MRNN)-based method for continuous Mandarin speech recognition (CMSR) is proposed. The MRNN recognizer is composed of four main modules. The first is a sub-MRNN module whose function is to generate discriminant functions for all 412 base-syllables. It accomplishes the task by using four recurrent neural network (RNN) submodules. The second is an RNN module which is designed to detect syllable boundaries for providing timing cues in order to help solve the time-alignment problem. The third is also an RNN module whose function is to generate discriminant functions for 143 intersyllable diphone-like units to compensate the intersyllable coarticulation effect. The fourth is a dynamic programming (DP)-based recognition search module. Its function is to integrate the other three modules and solve the time-alignment problem for generating the recognized base-syllable sequence. A new multilevel pruning scheme designed to speed up the recognition process is also proposed. The whole MRNN can be trained by a sophisticated three-stage minimum classification error/generalized probabilistic descent (MCE/GPD) algorithm. Experimental results showed that the proposed method performed better than the maximum likelihood (ML)-trained hidden Markov model (HMM) method and is comparable to the MCE/GPD-trained HMM method. The multilevel pruning scheme was also found to be very efficient

Published in:

IEEE Transactions on Speech and Audio Processing  (Volume:9 ,  Issue: 3 )