Gender effect in trait recognition

Mohamed A. Bencherif; Mansour Alsulaiman; Ghulam Muhammad; Zulfiqar Ali; Awais Mahmood; Mohamed Faisal

Gender effect in trait recognition

Mohamed A. Bencherif, Mansour Alsulaiman, Ghulam Muhammad, Zulfiqar Ali, Awais Mahmood, Mohamed Faisal

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

Abstract

This paper investigates the gender effect in speaker trait recognition especially in likability and personality detection. The acoustic features, classification methods, and feature selection techniques are adopted from the prescribed platform of the Interspeech 2012 Speaker Trait Challenge. In the proposed method, first we separate the files according to gender. Then features and classifiers are applied on gender dependent cases. In the experiments, we find that gender dependent trait recognition is higher than gender independent cases. We also find that the features and classification methods for male and female are different from the best cases. Our proposed technique outperforms the baseline result provided in the challenge in both likability and personality detection.

Original language	English
Pages	676-679
Number of pages	4
Publication status	Published (in print/issue) - 1 Jan 2012
Event	2012 World Congress on Engineering and Computer Science, WCECS 2012 - San Francisco, United States Duration: 24 Oct 2012 → 26 Oct 2012

Conference

Conference	2012 World Congress on Engineering and Computer Science, WCECS 2012
Country/Territory	United States
City	San Francisco
Period	24/10/12 → 26/10/12

Keywords

Feature selection
Likability
Personality
Speaker trait recognition

Cite this

@conference{3f9cd5b4652b4af38ec1f450c30d61df,

title = "Gender effect in trait recognition",

abstract = "This paper investigates the gender effect in speaker trait recognition especially in likability and personality detection. The acoustic features, classification methods, and feature selection techniques are adopted from the prescribed platform of the Interspeech 2012 Speaker Trait Challenge. In the proposed method, first we separate the files according to gender. Then features and classifiers are applied on gender dependent cases. In the experiments, we find that gender dependent trait recognition is higher than gender independent cases. We also find that the features and classification methods for male and female are different from the best cases. Our proposed technique outperforms the baseline result provided in the challenge in both likability and personality detection.",

keywords = "Feature selection, Likability, Personality, Speaker trait recognition",

author = "Bencherif, {Mohamed A.} and Mansour Alsulaiman and Ghulam Muhammad and Zulfiqar Ali and Awais Mahmood and Mohamed Faisal",

year = "2012",

month = jan,

day = "1",

language = "English",

pages = "676--679",

note = "2012 World Congress on Engineering and Computer Science, WCECS 2012 ; Conference date: 24-10-2012 Through 26-10-2012",

}

TY - CONF

T1 - Gender effect in trait recognition

AU - Bencherif, Mohamed A.

AU - Alsulaiman, Mansour

AU - Muhammad, Ghulam

AU - Ali, Zulfiqar

AU - Mahmood, Awais

AU - Faisal, Mohamed

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This paper investigates the gender effect in speaker trait recognition especially in likability and personality detection. The acoustic features, classification methods, and feature selection techniques are adopted from the prescribed platform of the Interspeech 2012 Speaker Trait Challenge. In the proposed method, first we separate the files according to gender. Then features and classifiers are applied on gender dependent cases. In the experiments, we find that gender dependent trait recognition is higher than gender independent cases. We also find that the features and classification methods for male and female are different from the best cases. Our proposed technique outperforms the baseline result provided in the challenge in both likability and personality detection.

AB - This paper investigates the gender effect in speaker trait recognition especially in likability and personality detection. The acoustic features, classification methods, and feature selection techniques are adopted from the prescribed platform of the Interspeech 2012 Speaker Trait Challenge. In the proposed method, first we separate the files according to gender. Then features and classifiers are applied on gender dependent cases. In the experiments, we find that gender dependent trait recognition is higher than gender independent cases. We also find that the features and classification methods for male and female are different from the best cases. Our proposed technique outperforms the baseline result provided in the challenge in both likability and personality detection.

KW - Feature selection

KW - Likability

KW - Personality

KW - Speaker trait recognition

UR - http://www.scopus.com/inward/record.url?scp=85049889153&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85049889153

SP - 676

EP - 679

T2 - 2012 World Congress on Engineering and Computer Science, WCECS 2012

Y2 - 24 October 2012 through 26 October 2012

ER -

Gender effect in trait recognition

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this