Temporal decomposition and acoustic-phonetic decoding of speech
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 445-448
- https://doi.org/10.1109/icassp.1988.196614
Abstract
The automatic recognition of continuous speech may use a symbolic representation of the acoustic signal in order to facilitate lexical access. The allophones of the language form a practical set of symbols. A major issue is a reliable localisation of these units in the speech stream and their identification. Localisation is obtained using a robust implementation of temporal decomposition, a technique originally proposed by Atal (1983), for speech coding. Speech is decomposed in terms of overlapping events characterized by both a spectral target and a time-limited interpolation function. An undershot target may be reestimated using neighbours and the associated functions. The possibility of undoing the effects of coarticulation is the major contribution of this work. The identification of these corrected targets is therefore possible with no further contextual rules. The recognition of spelled surnames (letters of the alphabet) is used for evaluation. 76% of correct phones allow 70% of correct letters.Keywords
This publication has 2 references indexed in Scilit:
- Modeling spectral speech transitions using temporal decomposition techniquesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Steady part recognition of continuous speech for acoustic-phonetic decodingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005