Title: SPEECH RECOGNITION WITH HIERARCHICAL RECURRENT NEURAL NETWORKS
Authors: CHEN, WY
LIAO, YF
CHEN, SH
交大名義發表
電信工程研究所
National Chiao Tung University
Institute of Communications Engineering
Keywords: SPEECH RECOGNITION;HIERARCHICAL;RECURRENT NEURAL NETWORKS;GENERALIZED PROBABILISTIC DESCENT;DISCRIMINATIVE TRAINING
Issue Date: 1-Jun-1995
Abstract: A hierarchical recurrent neural network (HRNN)for speech recognition is presented. The HRNN is trained by a generalized probabilistic descent (GPD) algorithm. Consequently, the difficulty of empirically selecting an appropriate target function for training RNNs can be avoided. Results obtained in this study indicate the proposed HRNN has the advantages of being capable of absorbing the temporal variation of speech patterns as well as possessing effective discrimination capabilities. The scaling problem of RNNs is also greatly reduced. Additionally, a realization of the system using initial/final sub-syllable models for isolated Mandarin syllable recognition is also undertaken for verifying its effectiveness. The effectiveness of the proposed HRNN is confirmed by the experimental results.
URI: http://hdl.handle.net/11536/1903
ISSN: 0031-3203
Journal: PATTERN RECOGNITION
Volume: 28
Issue: 6
Begin Page: 795
End Page: 805
Appears in Collections:Articles


Files in This Item:

  1. A1995RD17400001.pdf