Segmental Modeling Using a Continuous Mixture of Non-parametric Models

Jacob Goldberger; David Burshtein; Horacio Franco

Segmental Modeling Using a Continuous Mixture of Non-parametric Models

Jacob Goldberger, David Burshtein, Horacio Franco

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

The aim of the research described in this paper is to overcome the modeling limitation of conventional hidden Markov models. We present a segmental model that consists of two elements. The first is a nonparametric representation of both the mean and variance trajectories, which describes the local dynamics. The second element is some parameterized transformation (e.g., random shift) of the trajectory that is global to the segment and models long-term variations such as speaker identity.

Original language	English
Pages	1195-1198
Number of pages	4
State	Published - 1997
Externally published	Yes
Event	5th European Conference on Speech Communication and Technology, EUROSPEECH 1997 - Rhodes, Greece Duration: 22 Sep 1997 → 25 Sep 1997

Conference

Conference	5th European Conference on Speech Communication and Technology, EUROSPEECH 1997
Country/Territory	Greece
City	Rhodes
Period	22/09/97 → 25/09/97

Bibliographical note

Publisher Copyright:
© 1997 5th European Conference on Speech Communication and Technology, EUROSPEECH 1997. All rights reserved.

Funding

We gratefully acknowledge partial support for this work from ARPA through Office of Naval Research Contract N00014-94-C-0181.

Funders	Funder number
Office of Naval Research	N00014-94-C-0181
Advanced Research Projects Agency

Cite this

@conference{82a5069a8a5742419834d51c6b69b1be,

title = "Segmental Modeling Using a Continuous Mixture of Non-parametric Models",

abstract = "The aim of the research described in this paper is to overcome the modeling limitation of conventional hidden Markov models. We present a segmental model that consists of two elements. The first is a nonparametric representation of both the mean and variance trajectories, which describes the local dynamics. The second element is some parameterized transformation (e.g., random shift) of the trajectory that is global to the segment and models long-term variations such as speaker identity.",

author = "Jacob Goldberger and David Burshtein and Horacio Franco",

note = "Publisher Copyright: {\textcopyright} 1997 5th European Conference on Speech Communication and Technology, EUROSPEECH 1997. All rights reserved.; 5th European Conference on Speech Communication and Technology, EUROSPEECH 1997 ; Conference date: 22-09-1997 Through 25-09-1997",

year = "1997",

language = "אנגלית",

pages = "1195--1198",

}

TY - CONF

T1 - Segmental Modeling Using a Continuous Mixture of Non-parametric Models

AU - Goldberger, Jacob

AU - Burshtein, David

AU - Franco, Horacio

PY - 1997

Y1 - 1997

N2 - The aim of the research described in this paper is to overcome the modeling limitation of conventional hidden Markov models. We present a segmental model that consists of two elements. The first is a nonparametric representation of both the mean and variance trajectories, which describes the local dynamics. The second element is some parameterized transformation (e.g., random shift) of the trajectory that is global to the segment and models long-term variations such as speaker identity.

AB - The aim of the research described in this paper is to overcome the modeling limitation of conventional hidden Markov models. We present a segmental model that consists of two elements. The first is a nonparametric representation of both the mean and variance trajectories, which describes the local dynamics. The second element is some parameterized transformation (e.g., random shift) of the trajectory that is global to the segment and models long-term variations such as speaker identity.

UR - http://www.scopus.com/inward/record.url?scp=4544236098&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:4544236098

SP - 1195

EP - 1198

T2 - 5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Y2 - 22 September 1997 through 25 September 1997

ER -

Segmental Modeling Using a Continuous Mixture of Non-parametric Models

Abstract

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this