Construction of Phoneme Models -Model Search Of Hidden Markov Models- (1993)
| Venue: | In International Workshop on Intelligent Signal Processing and Communication Systems |
| Citations: | 5 - 0 self |
BibTeX
@INPROCEEDINGS{Ikeda93constructionof,
author = {Shiro Ikeda},
title = {Construction of Phoneme Models -Model Search Of Hidden Markov Models-},
booktitle = {In International Workshop on Intelligent Signal Processing and Communication Systems},
year = {1993}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
The author proposes an algorithm to define a structure of a HMM(hidden Markov model)[1]. HMMs are widely used in the speech recognition systems and at that time structures are usually determined according to the heuristic knowledge.In this article this problem is treated as so-called "model selection" problem in statistics. Two recognition experiments using the algorithm are shown. First, artificial data then, ATR speech database are used for the source. Through these experiments, the author shows that such model selection is effective.
Citations
| 1131 | A new look at the statistical model identification - Akaike - 1974 |
| 976 | An algorithm for vector quantizer design - Linde, Buzo, et al. - 1980 |
| 176 | Automatic Speech Recognition: The Development of the SPHINX System - Lee - 1989 |
| 18 | Distribution of informational statistics and a criterion of model fitting - Takeuchi - 1976 |
| 2 | Construction of phone HMM using model search method - Ikeda - 1993 |
| 1 | Distributionof inftributi statistics and a criterionof model fitting - Takeuchi - 1976 |
| 1 | Manual Segmentation of Spectrogram for the AcousticPhonetic Transcriptions - Takeda, Sagisaka, et al. - 1988 |
