Learning speaker normalization using semisupervised manifold alignment

Andrew R. Plummer; Mary E. Beckman; Mikhail Belkin; Eric Fosler-Lussier; Benjamin Munson

Learning speaker normalization using semisupervised manifold alignment

Andrew R. Plummer, Mary E. Beckman, Mikhail Belkin, Eric Fosler-Lussier, Benjamin Munson

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

Abstract

As a child acquires language, he or she: perceives acoustic information in his or her surrounding environment; identifies portions of the ambient acoustic information as language-related; and associates that language-related information with his or her perception of his or her own language-related acoustic productions. The present work models the third task. We use a semisupervised alignment algorithm based on manifold learning. We discuss the concepts behind this approach, and the application of the algorithm to this task. We present experimental evidence indicating the usefulness of manifold alignment in learning speaker normalization.

Original language	English (US)
Pages	2918-2921
Number of pages	4
State	Published - Dec 1 2010
Event	11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba, Japan Duration: Sep 26 2010 → Sep 30 2010

Other

Other	11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
Country/Territory	Japan
City	Makuhari, Chiba
Period	9/26/10 → 9/30/10

Keywords

Language acquisition
Manifold alignment
Speaker normalization

Find It

Find It at U of M Libraries

Cite this

Learning speaker normalization using semisupervised manifold alignment. / Plummer, Andrew R.; Beckman, Mary E.; Belkin, Mikhail et al.
2010. 2918-2921 Paper presented at 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan.

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

@conference{e5f26497b73d44f2a0a682ea684eb6ec,

title = "Learning speaker normalization using semisupervised manifold alignment",

abstract = "As a child acquires language, he or she: perceives acoustic information in his or her surrounding environment; identifies portions of the ambient acoustic information as language-related; and associates that language-related information with his or her perception of his or her own language-related acoustic productions. The present work models the third task. We use a semisupervised alignment algorithm based on manifold learning. We discuss the concepts behind this approach, and the application of the algorithm to this task. We present experimental evidence indicating the usefulness of manifold alignment in learning speaker normalization.",

keywords = "Language acquisition, Manifold alignment, Speaker normalization",

author = "Plummer, {Andrew R.} and Beckman, {Mary E.} and Mikhail Belkin and Eric Fosler-Lussier and Benjamin Munson",

year = "2010",

month = dec,

day = "1",

language = "English (US)",

pages = "2918--2921",

note = "11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 ; Conference date: 26-09-2010 Through 30-09-2010",

}

TY - CONF

T1 - Learning speaker normalization using semisupervised manifold alignment

AU - Plummer, Andrew R.

AU - Beckman, Mary E.

AU - Belkin, Mikhail

AU - Fosler-Lussier, Eric

AU - Munson, Benjamin

PY - 2010/12/1

Y1 - 2010/12/1

N2 - As a child acquires language, he or she: perceives acoustic information in his or her surrounding environment; identifies portions of the ambient acoustic information as language-related; and associates that language-related information with his or her perception of his or her own language-related acoustic productions. The present work models the third task. We use a semisupervised alignment algorithm based on manifold learning. We discuss the concepts behind this approach, and the application of the algorithm to this task. We present experimental evidence indicating the usefulness of manifold alignment in learning speaker normalization.

AB - As a child acquires language, he or she: perceives acoustic information in his or her surrounding environment; identifies portions of the ambient acoustic information as language-related; and associates that language-related information with his or her perception of his or her own language-related acoustic productions. The present work models the third task. We use a semisupervised alignment algorithm based on manifold learning. We discuss the concepts behind this approach, and the application of the algorithm to this task. We present experimental evidence indicating the usefulness of manifold alignment in learning speaker normalization.

KW - Language acquisition

KW - Manifold alignment

KW - Speaker normalization

UR - http://www.scopus.com/inward/record.url?scp=79959821378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959821378&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:79959821378

SP - 2918

EP - 2921

T2 - 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010

Y2 - 26 September 2010 through 30 September 2010

ER -

Learning speaker normalization using semisupervised manifold alignment

Abstract

Other

Keywords

Find It

Other files and links

Fingerprint

Cite this