For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
An SVQ-HMM Training Method Using Simultaneous Generative Histogram
Yasuhisa HAYASHI Satoshi KONDO Nobuyuki TAKASU Akio OGIHARA Shojiro YONEDA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1992/07/25
Print ISSN: 0916-8508
Type of Manuscript: Special Section LETTER (Special Section on the 1992 IEICE Spring Conference)
speech recognition, separate vector quantization, hidden Markov model, simultaneous generative histogram,
Full Text: PDF(212KB)>>
This study proposes a new training method for hidden Markov model with separate vector quantization (SVQ-HMM) in speech recognition. The proposed method uses the correlation of two different kinds of features: cepstrum and delta-cepstrum. The correlation is used to decrease the number of reestimation for two features thus the total computation time for training models decreases. The proposed method is applied to Japanese language isolated dgit recognition.