Browsing by Author "CHEN, WY"

Now showing 1 - 6 of 6

A NEW METHOD FOR DETERMINING THE TERMINAL SERIES RESISTANCES AND HIGH-INJECTION COEFFICIENT OF BIPOLAR-TRANSISTORS IN CMOS INTEGRATED-CIRCUITS FOR COMPUTER-AIDED CIRCUIT MODELING
(1988-05-01)
YANG, YH
;
WU, CY
;
CHEN, WY
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
A PRECISION EXPERIMENT ON ELECTRONS, PHOTONS AND MUONS AT LHC
(1993-02-01)
AZIZ, T
;
BOCK, R
;
BRAUNSCHWEIG, W
;
GEULIG, E
;
HILGERS, K
We describe the upgrade of the L3 detector for running at LHC. The principle goals are the precise measurement of electrons, photons and muons.
APPLICATION OF A GENERALIZED PROBABILISTIC DESCENT METHOD TO RECURRENT NEURAL NETWORK BASED SPEECH RECOGNITION
(1994)
CHEN, SH
;
LIAO, YF
;
CHEN, WY
;
交大名義發表
;
National Chiao Tung University
GENERALIZED MINIMAL DISTORTION SEGMENTATION FOR ANN-BASED SPEECH RECOGNITION
(1995-03-01)
CHEN, SH
;
CHEN, WY
;
交大名義發表
;
電信工程研究所
;
National Chiao Tung University
A generalized minimal distortion segmentation algorithm is proposed to solve the time alignment problem for ANN-based speech recognition. By modeling dynamics of spectral information of an acoustic segment with smooth curves obtained by orthonormal polynomial expansion, a speech signal is optimally divided into segments and then recognized by an MLP recognizer. Experimental results showed that the proposed method outperforms the standard CDHMM method.
SPEAKER-INDEPENDENT MANDARINE PLOSIVE RECOGNITION WITH DYNAMIC FEATURES AND MULTILAYER PERCEPTRONS
(1995-02-16)
CHEN, WY
;
CHEN, SH
;
交大名義發表
;
電信工程研究所
;
National Chiao Tung University
A new method for recognising plosives in isolated Mandarin syllables is discussed in the Letter. After automatically detecting the plosive segment of the input utterance, some dynamic features are extracted from its spectral parameter contours using orthonormal polynomial transforms. Next, an MLP trained with an algorithm based on a minimum error criterion is employed to distinguish plosives using these features. A promising recognition rare of 73.6% is achieved in a speaker-independent test using a database containing utterances of 110 syllables uttered by 100 speakers.
SPEECH RECOGNITION WITH HIERARCHICAL RECURRENT NEURAL NETWORKS
(1995-06-01)
CHEN, WY
;
LIAO, YF
;
CHEN, SH
;
交大名義發表
;
電信工程研究所
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.