Browsing by Author "WANG, YR"

Now showing 1 - 3 of 3

TONE RECOGNITION OF CONTINUOUS MANDARINE SPEECH ASSISTED WITH PROSODIC INFORMATION
(1994-11-01)
WANG, YR
;
CHEN, SH
;
電信工程研究所
;
電信研究中心
;
Institute of Communications Engineering
In this paper, a simple recurrent neural network (SRNN) is employed to model the prosody of continuous Mandarin speech to assist tone recognition. For each syllable in continuous speech, several acoustic features carrying prosodic information are extracted and taken as inputs to the SRNN. If proper linguistic features extracted from the context of the syllable are set as output targets, the SRNN can learn to represent the prosodic state of the utterance at the syllable using its hidden nodes. Outputs of the hidden nodes then serve as additional recognition features to assist recognition of the tone of the syllable. The performance of the proposed tone recognition approach was examined by simulation on a multilayer perception (MLP)-based speaker-dependent tone recognition task. The recognition rate was improved from 91.38% to 93.10%. The SRNN prosodic model is further analyzed to exploit the linguistic meaning of prosodic states. By vector quantizing the outputs of the hidden nodes of the SRNN, a finite-state automata that roughly represents the mechanism of human prosody pronunciation can be obtained.
TONE RECOGNITION OF CONTINUOUS MANDARINE SPEECH-BASED ON NEURAL NETWORKS
(1995-03-01)
CHEN, SH
;
WANG, YR
;
交大名義發表
;
電信工程研究所
;
National Chiao Tung University
Several neural network-based tone recognition schemes for continuous Mandarin speech are discussed. A basic MLP tone recognizer using recognition features extracted from the processing syllable is first introduced. Then, some additional features extracted from neighboring syllables are added to compensate for the coarticulation effect. It is then further improved to compensate for the effect of sandhi rules of tone pronunciation by including tone information of neighboring syllables. The recognition criterion is now changed to find the best tone sequence that minimizes the total risk that simultaneously considers tone recognition of all syllables in the input utterance. Last, two approaches using HCNN and HSMLP, respectively, to model the intonation pattern as a hidden Markov chain for assisting tone recognition are proposed. The effectiveness of these schemes was confirmed by simulations on a speaker-independent tone recognition task. A recognition rate of 86.72% was achieved.
VECTOR QUANTIZATION OF PITCH INFORMATION IN MANDARINE SPEECH
(1990-09-01)
CHEN, SH
;
WANG, YR
;
電信工程研究所
;
電信研究中心
;
Institute of Communications Engineering