Rapid and brief communication: Combining classifier decisions for robust speaker identification

Authors:
Daniel J. Mashao;Marshalleno Skosan
Affiliations:
Speech Technology And Research (STAR), University of Cape Town, Rondebosch 7701, South Africa;Speech Technology And Research (STAR), University of Cape Town, Rondebosch 7701, South Africa
Venue:
Pattern Recognition
Year:
2006

Citing 8
Cited 16

Speaker identification and verification using Gaussian mixture speaker models

Speech Communication
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Pattern Recognition: A Review

IEEE Transactions on Pattern Analysis and Machine Intelligence
The NIST speaker recognition evaluation - overview methodology, systems, results, perspective

Speech Communication - Speaker recognition and its commercial and forensic applications
Computations and evaluations of an optimal feature-set for an hmm-based recognizer

Computations and evaluations of an optimal feature-set for an hmm-based recognizer
Fitting the Mel scale

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Corpora for the evaluation of speaker recognition systems

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Auditory nerve representation as a front-end for speech recognition in a noisy environment

Computer Speech and Language

Automated speech analysis applied to laryngeal disease categorization

Computer Methods and Programs in Biomedicine
Speaker identification using discrete wavelet packet transform technique with irregular decomposition

Expert Systems with Applications: An International Journal
A generalized adaptive ensemble generation and aggregation approach for multiple classifier systems

Pattern Recognition
Speaker identification based on the frame linear predictive coding spectrum technique

Expert Systems with Applications: An International Journal
Data dependency in multiple classifier systems

Pattern Recognition
Combination of multiple classifiers for post-placement quality inspection of components: A comparative study

Information Fusion
Selecting features from multiple feature sets for SVM committee-based screening of human larynx

Expert Systems with Applications: An International Journal
Survey on speech emotion recognition: Features, classification schemes, and databases

Pattern Recognition
Comparison of the impact of some Minkowski metrics on VQ/GMM based speaker recognition

Computers and Electrical Engineering
Subsegmental, segmental and suprasegmental processing of linear prediction residual for speaker information

International Journal of Speech Technology
Wavelet entropy and neural network for text-independent speaker identification

Engineering Applications of Artificial Intelligence
A hybrid data-fusion system using modal data and probabilistic neural network for damage detection

Advances in Engineering Software
Robust speaker identification using ensembles of kernel principal component analysis

HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part I
Speaker verification using excitation source information

International Journal of Speech Technology
Audio-Visual feature fusion for speaker identification

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I
From static to dynamic ensemble of classifiers selection: Application to Arabic handwritten recognition

International Journal of Knowledge-based and Intelligent Engineering Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this work, we combine the decisions of two classifiers as an alternative means of improving the performance of a speaker recognition system in adverse environments. The difference between these classifiers is in their feature-sets. One system is based on the popular mel-frequency cepstral coefficients (MFCC) and the other on the new parametric feature-sets (PFS) algorithm. The feature-vectors both have mel-scale spectral warping and are computed in the cepstral domain but the feature-sets differs in the use of spectral filters and compressions. The performance of the classifier is not much different in recognition rates terms but they are complementary. This shows that there is information that is not captured in the popular mel-frequency cepstral coefficients (MFCC), and the parametric feature-sets (PFS) is able to add further information for improved performance. Several ways of combining these classifiers gives significant improvements in a speaker identification task using a very large telephone degraded NTIMIT database.