Automatic speech-based classification of gender, age and accent

Authors:
Phuoc Nguyen;Dat Tran;Xu Huang;Dharmendra Sharma
Affiliations:
Faculty of Information Sciences and Engineering, University of Canberra, ACT, Australia;Faculty of Information Sciences and Engineering, University of Canberra, ACT, Australia;Faculty of Information Sciences and Engineering, University of Canberra, ACT, Australia;Faculty of Information Sciences and Engineering, University of Canberra, ACT, Australia
Venue:
PKAW'10 Proceedings of the 11th international conference on Knowledge management and acquisition for smart systems and services
Year:
2010

Citing 9
Cited 0

Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Broadcast News Transcription Using HTK

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Improved acoustic modeling with the SPHINX speech recognition system

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Fuzzy Vector Quantization for Network Intrusion Detection

GRC '07 Proceedings of the 2007 IEEE International Conference on Granular Computing
Speaker Characteristics

Speaker Classification I
Acoustic Analysis of Adult Speaker Age

Speaker Classification I
Higher-Level Features in Speaker Recognition

Speaker Classification I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an automatic speech-based classification scheme to classify speaker characteristics. In the training phase, speech data are grouped into speaker groups according to speakers' gender, age and accent. Voice features are then extracted to feature vectors which are used to train speaker characteristic models with different techniques which are Vector Quantization, Gaussian Mixture Model and Support Vector Machine. Fusion of classification results from those groups is then performed to obtain final classification results for each characteristic. The Australian National Database of Spoken Language (ANDOSL) corpus was used for evaluation of gender, age and accent classification. Experiments showed high performance for the proposed classification scheme.