TRAP-TANDEM: Data-driven extraction of temporal features from speechReport as inadecuate




TRAP-TANDEM: Data-driven extraction of temporal features from speech - Download this document for free, or read online. Document in PDF available to download.

Presented at: large part published in Proceedings of ASRU-2003 Published in: large part published in Proceedings of ASRU-2003, num. 50 Publication date: 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.

Keywords: speech Note: IDIAP-RR 03-50 Reference EPFL-CONF-82959





Author: Hermansky, Hynek

Source: https://infoscience.epfl.ch/record/82959?ln=en







Related documents