Combined Features and Kernel Design for Noise Robust Phoneme Classification Using Support Vector Machines

TY - JOUR

T1 - Combined Features and Kernel Design for Noise Robust Phoneme Classification Using Support Vector Machines

AU - Yousafzai, Jibran

AU - Sollich, Peter

AU - Cvetkovic, Zoran

AU - Yu, Bin

PY - 2011

Y1 - 2011

N2 - This paper proposes methods for combining cepstral and acoustic waveform representations for a front-end of support vector machine (SVM)-based speech recognition systems that are robust to additive noise. The key issue of kernel design and noise adaptation for the acoustic waveform representation is addressed first. Cepstral and acoustic waveform representations are then compared on a phoneme classification task. Experiments show that the cepstral features achieve very good performance in low noise conditions, but suffer severe performance degradation already at moderate noise levels. Classification in the acoustic waveform domain, on the other hand, is less accurate in low noise but exhibits a more robust behavior in high noise conditions. A combination of the cepstral and acoustic waveform representations achieves better classification performance than either of the individual representations over the entire range of noise levels tested, down to -18-dB SNR.

AB - This paper proposes methods for combining cepstral and acoustic waveform representations for a front-end of support vector machine (SVM)-based speech recognition systems that are robust to additive noise. The key issue of kernel design and noise adaptation for the acoustic waveform representation is addressed first. Cepstral and acoustic waveform representations are then compared on a phoneme classification task. Experiments show that the cepstral features achieve very good performance in low noise conditions, but suffer severe performance degradation already at moderate noise levels. Classification in the acoustic waveform domain, on the other hand, is less accurate in low noise but exhibits a more robust behavior in high noise conditions. A combination of the cepstral and acoustic waveform representations achieves better classification performance than either of the individual representations over the entire range of noise levels tested, down to -18-dB SNR.

U2 - 10.1109/TASL.2010.2090657

DO - 10.1109/TASL.2010.2090657

M3 - Article

VL - 19

SP - 1396

EP - 1407

JO - Ieee Transactions On Audio Speech And Language Processing

JF - Ieee Transactions On Audio Speech And Language Processing

IS - 5

M1 - 5618550

ER -