Fuzzy support vector machines for age and gender classification

Research output: A Conference proceeding or a Chapter in BookConference contribution

10 Citations (Scopus)

Abstract

Support vector machine (SVM) has been proven as a powerful tool for solving age and gender classi?cation problems. However, SVM is sensitive to noise and outliers. In this paper we propose a new fuzzy SVM based on an assumption that training data points should not be treated equally to avoid the problem of sensitivity to noise and outliers. This can be achieved by assigning a fuzzy membership as a weight to each training data point. A method to calculate fuzzy memberships is also presented. Experiments performed on the a Gender corpus for INTERSPEECH 2010 Paralinguistic Challenge show that the proposed fuzzy SVM can improve age and gender classification accuracy.
Original languageEnglish
Title of host publicationINTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association
EditorsTakao Kobayashi, Keikichi Hirose, Satoshi Nakamura
Place of PublicationLisbon, Portugal
PublisherInternational Speech Communication Association
Pages2806-2809
Number of pages4
ISBN (Print)9781617821233
Publication statusPublished - 2010
EventINTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association - Makuhari, Makuhari, Japan
Duration: 26 Sep 201030 Sep 2010

Conference

ConferenceINTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association
CountryJapan
CityMakuhari
Period26/09/1030/09/10

Fingerprint

Support vector machines
Positive ions
Experiments

Cite this

Tran, D., & Sharma, D. (2010). Fuzzy support vector machines for age and gender classification. In T. Kobayashi, K. Hirose, & S. Nakamura (Eds.), INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association (pp. 2806-2809). Lisbon, Portugal: International Speech Communication Association.
Tran, Dat ; Sharma, Dharmendra. / Fuzzy support vector machines for age and gender classification. INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association. editor / Takao Kobayashi ; Keikichi Hirose ; Satoshi Nakamura. Lisbon, Portugal : International Speech Communication Association, 2010. pp. 2806-2809
@inproceedings{b956510a9a954c138738bea6a520fb75,
title = "Fuzzy support vector machines for age and gender classification",
abstract = "Support vector machine (SVM) has been proven as a powerful tool for solving age and gender classi?cation problems. However, SVM is sensitive to noise and outliers. In this paper we propose a new fuzzy SVM based on an assumption that training data points should not be treated equally to avoid the problem of sensitivity to noise and outliers. This can be achieved by assigning a fuzzy membership as a weight to each training data point. A method to calculate fuzzy memberships is also presented. Experiments performed on the a Gender corpus for INTERSPEECH 2010 Paralinguistic Challenge show that the proposed fuzzy SVM can improve age and gender classification accuracy.",
author = "Dat Tran and Dharmendra Sharma",
year = "2010",
language = "English",
isbn = "9781617821233",
pages = "2806--2809",
editor = "Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura",
booktitle = "INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association",
publisher = "International Speech Communication Association",

}

Tran, D & Sharma, D 2010, Fuzzy support vector machines for age and gender classification. in T Kobayashi, K Hirose & S Nakamura (eds), INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association. International Speech Communication Association, Lisbon, Portugal, pp. 2806-2809, INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association, Makuhari, Japan, 26/09/10.

Fuzzy support vector machines for age and gender classification. / Tran, Dat; Sharma, Dharmendra.

INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association. ed. / Takao Kobayashi; Keikichi Hirose; Satoshi Nakamura. Lisbon, Portugal : International Speech Communication Association, 2010. p. 2806-2809.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Fuzzy support vector machines for age and gender classification

AU - Tran, Dat

AU - Sharma, Dharmendra

PY - 2010

Y1 - 2010

N2 - Support vector machine (SVM) has been proven as a powerful tool for solving age and gender classi?cation problems. However, SVM is sensitive to noise and outliers. In this paper we propose a new fuzzy SVM based on an assumption that training data points should not be treated equally to avoid the problem of sensitivity to noise and outliers. This can be achieved by assigning a fuzzy membership as a weight to each training data point. A method to calculate fuzzy memberships is also presented. Experiments performed on the a Gender corpus for INTERSPEECH 2010 Paralinguistic Challenge show that the proposed fuzzy SVM can improve age and gender classification accuracy.

AB - Support vector machine (SVM) has been proven as a powerful tool for solving age and gender classi?cation problems. However, SVM is sensitive to noise and outliers. In this paper we propose a new fuzzy SVM based on an assumption that training data points should not be treated equally to avoid the problem of sensitivity to noise and outliers. This can be achieved by assigning a fuzzy membership as a weight to each training data point. A method to calculate fuzzy memberships is also presented. Experiments performed on the a Gender corpus for INTERSPEECH 2010 Paralinguistic Challenge show that the proposed fuzzy SVM can improve age and gender classification accuracy.

M3 - Conference contribution

SN - 9781617821233

SP - 2806

EP - 2809

BT - INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association

A2 - Kobayashi, Takao

A2 - Hirose, Keikichi

A2 - Nakamura, Satoshi

PB - International Speech Communication Association

CY - Lisbon, Portugal

ER -

Tran D, Sharma D. Fuzzy support vector machines for age and gender classification. In Kobayashi T, Hirose K, Nakamura S, editors, INTERSPEECH 2010: 11th Annual Conference of the International Speech Communication Association. Lisbon, Portugal: International Speech Communication Association. 2010. p. 2806-2809