4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Syllable-level Desynchronisation of Phonetic Features for Speech Recognition

Katrin Kirchhoff

Technische Fakultšt, University of Bielefeld, Germany

This paper describes a novel approach to speech recognition which is based on phonetic features as basic recognition units and the delayed synchronisation of these features within a higher-level prosodic domain, viz. the syllable. The object of this approach is to avoid a rigid segmentation of the speech signal as it is usually carried out by standard segment-based recognition systems. The architectural setup of the system will be described, as well as evaluation tests carried out on a medium-sized corpus of spontaneous speech (German). Syllable and phoneme recognition results will be given and compared to recognition rates obtained by a standard triphone-based HMMrecogniser trained and tested on the same data set.

Full Paper

Bibliographic reference.  Kirchhoff, Katrin (1996): "Syllable-level desynchronisation of phonetic features for speech recognition", In ICSLP-1996, 2274-2276.