Robust parametric modeling of durations in hidden markov models

David Burshtein

doi:10.1109/89.496221

Robust parametric modeling of durations in hidden markov models

David Burshtein^*

^*Corresponding author for this work

School of Electrical Engineering

Deptartment of Electrical Engineering-Systems

Research output: Contribution to journal › Article › peer-review

46 Scopus citations

Abstract

A major weakness of conventional hidden Markov models is that they implicitly model state durations by a geometric distribution, which is usually inappropriate. This paper presents a modified Viterbi algorithm that, by incorporating proper state and word duration modeling, significantly reduces the string error rate of the conventional Viterbi algorithm for a speaker-independent, connected-digit string task. The algorithm has essentially the same computational requirements of the conventional Viterbi algorithm.

Original language	English
Pages (from-to)	240-242
Number of pages	3
Journal	IEEE Transactions on Speech and Audio Processing
Volume	4
Issue number	3
DOIs	https://doi.org/10.1109/89.496221
State	Published - 1996

Access to Document

10.1109/89.496221

Cite this

@article{fbbaa1b768a84e848a39f83ac2051b58,

title = "Robust parametric modeling of durations in hidden markov models",

abstract = "A major weakness of conventional hidden Markov models is that they implicitly model state durations by a geometric distribution, which is usually inappropriate. This paper presents a modified Viterbi algorithm that, by incorporating proper state and word duration modeling, significantly reduces the string error rate of the conventional Viterbi algorithm for a speaker-independent, connected-digit string task. The algorithm has essentially the same computational requirements of the conventional Viterbi algorithm.",

author = "David Burshtein",

year = "1996",

doi = "10.1109/89.496221",

language = "אנגלית",

volume = "4",

pages = "240--242",

journal = "IEEE Transactions on Speech and Audio Processing",

issn = "1063-6676",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Robust parametric modeling of durations in hidden markov models

AU - Burshtein, David

PY - 1996

Y1 - 1996

N2 - A major weakness of conventional hidden Markov models is that they implicitly model state durations by a geometric distribution, which is usually inappropriate. This paper presents a modified Viterbi algorithm that, by incorporating proper state and word duration modeling, significantly reduces the string error rate of the conventional Viterbi algorithm for a speaker-independent, connected-digit string task. The algorithm has essentially the same computational requirements of the conventional Viterbi algorithm.

AB - A major weakness of conventional hidden Markov models is that they implicitly model state durations by a geometric distribution, which is usually inappropriate. This paper presents a modified Viterbi algorithm that, by incorporating proper state and word duration modeling, significantly reduces the string error rate of the conventional Viterbi algorithm for a speaker-independent, connected-digit string task. The algorithm has essentially the same computational requirements of the conventional Viterbi algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0030149810&partnerID=8YFLogxK

U2 - 10.1109/89.496221

DO - 10.1109/89.496221

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0030149810

SN - 1063-6676

VL - 4

SP - 240

EP - 242

JO - IEEE Transactions on Speech and Audio Processing

JF - IEEE Transactions on Speech and Audio Processing

IS - 3

ER -

Robust parametric modeling of durations in hidden markov models

Abstract

Access to Document

Other files and links

Fingerprint

Cite this