SNR-dependent compression of enhanced Mel sub-band energies for compensation of noise effects on MFCC features

Authors:
Babak Nasersharif;Ahmad Akbari
Affiliations:
Research Center for Information Technology, Computer Engineering Department, Iran University of Science and Technology, University Road, Hengam Street, Resalat Square, Tehran, Iran;Research Center for Information Technology, Computer Engineering Department, Iran University of Science and Technology, University Road, Hengam Street, Resalat Square, Tehran, Iran
Venue:
Pattern Recognition Letters
Year:
2007

Citing 5
Cited 5

Root cepstral analysis: a unified view: application to speech processing in car noise environments

Speech Communication - Special issue on speech processing in adverse conditions
Robust speech recognition by normalization of the acoustic space

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Psychoacoustics: Facts and Models

Psychoacoustics: Facts and Models
Advanced Digital Signal Processing and Noise Reduction

Advanced Digital Signal Processing and Noise Reduction
Significance of group delay functions in spectrum estimation

IEEE Transactions on Signal Processing

Optimized discriminative transformations for speech features based on minimum classification error

Pattern Recognition Letters
Evolutionary cepstral coefficients

Applied Soft Computing
Evolutionary splines for cepstral filterbank optimization in phoneme classification

EURASIP Journal on Advances in Signal Processing - Special issue on biologically inspired signal processing: analyses, algorithms and applications
Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition

Speech Communication
Is masking a relevant aspect lacking in MFCC? A speaker verification perspective

Pattern Recognition Letters

Quantified Score

Hi-index	0.10

Visualization

Abstract

The Mel-frequency cepstral coefficients (MFCC) are most widely used features for speech recognition. But, their performance degrades in presence of additive noise. In this paper, we propose a noise compensation method for Mel sub-bands energies as well as MFCC features. This method includes two steps: Mel sub-band spectral subtraction and compression of Mel sub-band energies. In the compression step, we propose a sub-band SNR-dependent compression function. This function replaces logarithm function in conventional MFCC feature extraction. Experimental results show that the proposed method significantly improves performance of MFCC features in noisy conditions. It decreases word error rate about 70% in SNR value of 0dB for different types of additive noise.