8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Localized Spectro-Temporal Features for Automatic Speech Recognition

Michael Kleinschmidt

Universitšt Oldenburg, Germany

Recent results from physiological and psychoacoustic studies indicate that spectrally and temporally localized time-frequency envelope patterns form a relevant basis of auditory perception. This motivates new approaches to feature extraction for automatic speech recognition (ASR) which utilize two-dimensional spectro-temporal modulation filters. The paper provides a motivation and a brief overview on the work related to Localized Spectro-Temporal Features (LSTF). It further focuses on the Gabor feature approach, where a feature selection scheme is applied to automatically obtain a suitable set of Gabor-type features for a given task. The optimized feature sets are examined in ASR experiments with respect to robustness and their statistical properties are analyzed.

Full Paper

Bibliographic reference.  Kleinschmidt, Michael (2003): "Localized spectro-temporal features for automatic speech recognition", In EUROSPEECH-2003, 2573-2576.