Sciweavers

ICASSP
2010
IEEE

Robust spectro-temporal features based on autoregressive models of Hilbert envelopes

13 years 3 months ago
Robust spectro-temporal features based on autoregressive models of Hilbert envelopes
In this paper, we present a robust spectro-temporal feature extraction technique using autoregressive models (AR) of sub-band Hilbert envelopes. AR models of Hilbert envelopes are derived using frequency domain linear prediction (FDLP). From the sub-band Hilbert envelopes, spectral features are derived by integrating these envelopes in short-term frames and the temporal features are formed by converting these envelopes into modulation frequency components. The spectral and temporal feature streams are then combined at the phoneme posterior level and are used as the input features for a recognition system. For the proposed features, robustness is achieved by using novel techniques of noise compensation and gain normalization. Phoneme recognition experiments on telephone speech in the HTIMIT database show significant performance improvements for the proposed features when compared to other robust feature techniques (average relative reduction of 10.6 % in phoneme error rate). In additi...
Sriram Ganapathy, Samuel Thomas, Hynek Hermansky
Added 06 Dec 2010
Updated 06 Dec 2010
Type Conference
Year 2010
Where ICASSP
Authors Sriram Ganapathy, Samuel Thomas, Hynek Hermansky
Comments (0)