A New HMnet Construction Algorithm Requiring No Contextual Factors

Motoyuki SUZUKI; Shozo MAKINO; Akinori ITO; Hirotomo ASO; Hiroshi SHIMODAIRA

A New HMnet Construction Algorithm Requiring No Contextual Factors

Motoyuki SUZUKI, Shozo MAKINO, Akinori ITO, Hirotomo ASO, Hiroshi SHIMODAIRA

Full Text Views

0

Share
Cite this

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

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://globals.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 -