logo Idiap Research Institute        
 [BibTeX] [Marc21]
TRAP-TANDEM: Data-driven extraction of temporal features from speech
Type of publication: Idiap-RR
Citation: hynek-rr-03-50
Number: Idiap-RR-50-2003
Year: 2003
Institution: IDIAP
Address: Martigny, Switzerland
Note: large part published in Proceedings of ASRU-2003
Abstract: 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.
Userfields: ipdinar={2003}, ipdmembership={speech}, language={English},
Projects Idiap
Authors Hermansky, Hynek
Crossref by hynek-rr-03-50b
Added by: [UNK]
Total mark: 0
  • rr03-50.pdf
  • rr03-50.ps.gz