Combining Mel frequency Cepstral coefficients and fractal dimensions for automatic speech recognition

Authors:
Aitzol Ezeiza;Karmele López De Ipiña;Carmen Hernández;Nora Barroso
Affiliations:
Department of System Engineering and Automation, University of the Basque Country, Spain;Department of System Engineering and Automation, University of the Basque Country, Spain;Department of System Engineering and Automation, University of the Basque Country, Spain;Irunweb Enterprise, Auzolan, Irun, Spain
Venue:
NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing
Year:
2011

Citing 5
Cited 1

Approach to an irregular time series on the basis of the fractal theory

Physica D
Fractal aspects of speech signals: dimension and interpolation

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Fractal characteristic-based endpoint detection for whispered speech

SSIP'06 Proceedings of the 6th WSEAS International Conference on Signal, Speech and Image Processing
Analysis and classification of speech signals by generalized fractal dimension features

Speech Communication
Third-Order moments of filtered speech signals for robust speech recognition

NOLISP'05 Proceedings of the 3rd international conference on Non-Linear Analyses and Algorithms for Speech Processing

Hierarchical ANN system for stuttering identification

Computer Speech and Language

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hidden Markov Models and Mel Frequency Cepstral Coefficients (MFCC's) are a sort of standard for Automatic Speech Recognition (ASR) systems, but they fail to capture the nonlinear dynamics of speech that are present in the speech waveforms. The extra information provided by the nonlinear features could be especially useful when training data is scarce, or when the ASR task is very complex. In this work, the Fractal Dimension (FD) of the observed time series is combined with the traditional MFCC's in the feature vector in order to enhance the performance of two different ASR systems: the first one is a very simple one, with very few training examples, and the second one is a Large Vocabulary Continuous Speech Recognition System for Broadcast News.