Automatic classification of speaker characteristics

Phuoc Nguyen; Dat Tran; Xu Huang; Dharmendra Sharma

doi:10.1109/ICCE.2010.5670700

Automatic classification of speaker characteristics

Phuoc Nguyen, Dat Tran, Xu Huang, Dharmendra Sharma

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

4 Citations (Scopus)

106 Downloads (Pure)

Abstract

An automatic voice-based classification system of speaker characteristics including age, gender and accent is presented in this paper. Speakers are grouped according to their characteristics and their speech features are then extracted to train speaker group models using different classification techniques. Finally fusion of classification results for those speaker groups is performed to obtain results for each speaker characteristic. The ANDOSL Australian speech database consisting of 108 speakers and 21600 long utterances was used for system evaluation. Experiments showed high performance for the proposed classification of speaker characteristics.

Original language	English
Title of host publication	The Third International Conference on Communications and Electronics (ICCE 2010)
Editors	Roberto de Marea, Iwao Sasase, Nguyen Van Khang
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	147-152
Number of pages	6
ISBN (Print)	9781424470570
DOIs	https://doi.org/10.1109/ICCE.2010.5670700
Publication status	Published - 2010
Event	ICCE 2010: The Third International Conference on Communications and Electronics - Nha Trang, Viet Nam Duration: 11 Aug 2010 → 13 Aug 2010

Conference

Conference	ICCE 2010: The Third International Conference on Communications and Electronics
Country/Territory	Viet Nam
City	Nha Trang
Period	11/08/10 → 13/08/10

Access to Document

10.1109/ICCE.2010.5670700

PaperFinal published version, 531 KB

Cite this

@inproceedings{c72ef2222b394a1cae588fc8fe3c30ea,

title = "Automatic classification of speaker characteristics",

abstract = "An automatic voice-based classification system of speaker characteristics including age, gender and accent is presented in this paper. Speakers are grouped according to their characteristics and their speech features are then extracted to train speaker group models using different classification techniques. Finally fusion of classification results for those speaker groups is performed to obtain results for each speaker characteristic. The ANDOSL Australian speech database consisting of 108 speakers and 21600 long utterances was used for system evaluation. Experiments showed high performance for the proposed classification of speaker characteristics.",

author = "Phuoc Nguyen and Dat Tran and Xu Huang and Dharmendra Sharma",

year = "2010",

doi = "10.1109/ICCE.2010.5670700",

language = "English",

isbn = "9781424470570",

pages = "147--152",

editor = "{de Marea}, Roberto and Iwao Sasase and Khang, {Nguyen Van}",

booktitle = "The Third International Conference on Communications and Electronics (ICCE 2010)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "ICCE 2010: The Third International Conference on Communications and Electronics ; Conference date: 11-08-2010 Through 13-08-2010",

}

Nguyen, P, Tran, D , Huang, X & Sharma, D 2010, Automatic classification of speaker characteristics. in R de Marea, I Sasase & NV Khang (eds), The Third International Conference on Communications and Electronics (ICCE 2010). IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 147-152, ICCE 2010: The Third International Conference on Communications and Electronics, Nha Trang, Viet Nam, 11/08/10. https://doi.org/10.1109/ICCE.2010.5670700

Automatic classification of speaker characteristics. / Nguyen, Phuoc; Tran, Dat ; Huang, Xu et al.
The Third International Conference on Communications and Electronics (ICCE 2010). ed. / Roberto de Marea; Iwao Sasase; Nguyen Van Khang. USA: IEEE, Institute of Electrical and Electronics Engineers, 2010. p. 147-152.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Automatic classification of speaker characteristics

AU - Nguyen, Phuoc

AU - Tran, Dat

AU - Huang, Xu

AU - Sharma, Dharmendra

PY - 2010

Y1 - 2010

N2 - An automatic voice-based classification system of speaker characteristics including age, gender and accent is presented in this paper. Speakers are grouped according to their characteristics and their speech features are then extracted to train speaker group models using different classification techniques. Finally fusion of classification results for those speaker groups is performed to obtain results for each speaker characteristic. The ANDOSL Australian speech database consisting of 108 speakers and 21600 long utterances was used for system evaluation. Experiments showed high performance for the proposed classification of speaker characteristics.

AB - An automatic voice-based classification system of speaker characteristics including age, gender and accent is presented in this paper. Speakers are grouped according to their characteristics and their speech features are then extracted to train speaker group models using different classification techniques. Finally fusion of classification results for those speaker groups is performed to obtain results for each speaker characteristic. The ANDOSL Australian speech database consisting of 108 speakers and 21600 long utterances was used for system evaluation. Experiments showed high performance for the proposed classification of speaker characteristics.

U2 - 10.1109/ICCE.2010.5670700

DO - 10.1109/ICCE.2010.5670700

M3 - Conference contribution

SN - 9781424470570

SP - 147

EP - 152

BT - The Third International Conference on Communications and Electronics (ICCE 2010)

A2 - de Marea, Roberto

A2 - Sasase, Iwao

A2 - Khang, Nguyen Van

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

T2 - ICCE 2010: The Third International Conference on Communications and Electronics

Y2 - 11 August 2010 through 13 August 2010

ER -