REPORT hynek-rr-03-50/IDIAP TRAP-TANDEM: Data-driven extraction of temporal features from speech Hermansky, Hynek EXTERNAL http://publications.idiap.ch/attachments/reports/2003/rr03-50.pdf PUBLIC Idiap-RR-50-2003 2003 IDIAP Martigny, Switzerland large part published in Proceedings of ASRU-2003 Conventional features in automatic recognition of speech describe instantaneous shape of a short-time spectrum of speech. The TRAP-TANDEM features describe likelihoods of sub-word classess at a given time instant, derived from temporal trajectories of band-limited spectral densities in the vicinity of a given time instant. The paper presents some rationale behind the data-driven TRAP-TANDEM approach, briefly describes the technique, point to relevant oublications and summarizes results achieved so far.