In this work, nonlinear acoustic information is combined with traditional linear acoustic information to produce a noise-robust feature set for speech recognition. Classical acoustic modeling has relied on the assumption of linear acoustics where signal processing is performed in the signal's frequency domain. However, the performance of these systems suffers significant degradations when the acoustic data is contaminated with previously unseen noise. The objective of this thesis was to determine whether nonlinear dynamic invariants can boost speech recognition performance when combined with traditional acoustic features. Several experiments evaluate both clean and noisy speech data. The invariants resulted in a maximum relative increase of 11.1% for the clean evaluation set. However, an average relative decrease of 7.6% was observed for the noise-contaminated evaluation sets. The decrease in recognition performance with the use of dynamic invariants suggests that additional research is required for the filtering of phase spaces constructed from noisy time-series.
展开▼
