TRAP-TANDEM: data-driven extraction of temporal features from speech

Conventional features in automatic recognition of speech describe the instantaneous shape of a short-term spectrum of speech. The TRAP-TANDEM features describe the likelihood of sub-word classes at a given time instant, derived from temporal trajectories of band-limited spectral densities in the vicinity of the given instant. The paper presents some rationale behind the data-driven TRAP-TANDEM approach, briefly describes the technique, points to relevant publications and summarizes results achieved so far.