A New HMnet Construction Algorithm Requiring No Contextual Factors
Summary :
Many methods have been proposed for constructing context-dependent phoneme models using Hidden Markov Models (HMMs) to improve performance. These conventional methods require previously defined contextual factors. If these factors are deficient, the method exhibit poor recognition performance. In this paper, we propose a new construction algorithm for HMnet which does not require pre-defined contextual factors. Experiments demonstrated that the new algorithm could construct the HMnet even for the case that the Successive State Splitting (SSS) algorithm could not. The new algorithm produced better phoneme recognition characteristics than the SSS algorithm.
- Publication
- IEICE TRANSACTIONS on Information Vol.E78-D No.6 pp.662-668
- Publication Date
- 1995/06/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Spoken Language Processing)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Motoyuki SUZUKI, Shozo MAKINO, Akinori ITO, Hirotomo ASO, Hiroshi SHIMODAIRA, "A New HMnet Construction Algorithm Requiring No Contextual Factors" in IEICE TRANSACTIONS on Information,
vol. E78-D, no. 6, pp. 662-668, June 1995, doi: .
Abstract: Many methods have been proposed for constructing context-dependent phoneme models using Hidden Markov Models (HMMs) to improve performance. These conventional methods require previously defined contextual factors. If these factors are deficient, the method exhibit poor recognition performance. In this paper, we propose a new construction algorithm for HMnet which does not require pre-defined contextual factors. Experiments demonstrated that the new algorithm could construct the HMnet even for the case that the Successive State Splitting (SSS) algorithm could not. The new algorithm produced better phoneme recognition characteristics than the SSS algorithm.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_6_662/_p
Copy
@ARTICLE{e78-d_6_662,
author={Motoyuki SUZUKI, Shozo MAKINO, Akinori ITO, Hirotomo ASO, Hiroshi SHIMODAIRA, },
journal={IEICE TRANSACTIONS on Information},
title={A New HMnet Construction Algorithm Requiring No Contextual Factors},
year={1995},
volume={E78-D},
number={6},
pages={662-668},
abstract={Many methods have been proposed for constructing context-dependent phoneme models using Hidden Markov Models (HMMs) to improve performance. These conventional methods require previously defined contextual factors. If these factors are deficient, the method exhibit poor recognition performance. In this paper, we propose a new construction algorithm for HMnet which does not require pre-defined contextual factors. Experiments demonstrated that the new algorithm could construct the HMnet even for the case that the Successive State Splitting (SSS) algorithm could not. The new algorithm produced better phoneme recognition characteristics than the SSS algorithm.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - A New HMnet Construction Algorithm Requiring No Contextual Factors
T2 - IEICE TRANSACTIONS on Information
SP - 662
EP - 668
AU - Motoyuki SUZUKI
AU - Shozo MAKINO
AU - Akinori ITO
AU - Hirotomo ASO
AU - Hiroshi SHIMODAIRA
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 1995
AB - Many methods have been proposed for constructing context-dependent phoneme models using Hidden Markov Models (HMMs) to improve performance. These conventional methods require previously defined contextual factors. If these factors are deficient, the method exhibit poor recognition performance. In this paper, we propose a new construction algorithm for HMnet which does not require pre-defined contextual factors. Experiments demonstrated that the new algorithm could construct the HMnet even for the case that the Successive State Splitting (SSS) algorithm could not. The new algorithm produced better phoneme recognition characteristics than the SSS algorithm.
ER -
English
