Skip to Main content Skip to Navigation

Non-linear vector interpolation by neural network for phoneme identification in continuous speech

Abstract : The coorelation between vectors in a sequence of analysis frames are supposed to be specific to phonetic units in acoustic-phonetic decoding of speech. We propose non-linear vector interpolation techniques to represent this correlation and to recognize phonemes. The interpolation is based on the decomposition of a frame sequence into two parts and on the construction of a function that interpolates one part using information from the second part. According to quantities to be interpolated, three families of interpolator models are developed. In a recognition system, each phonetic symbol is associated with a non-linear vector interpolator which is trained to give minimum interpolation error for that specific phoneme. Multi-layer feedforward neural networks are used to implement the non-linear vector interpolators. For a continuous speech phoneme spotting test using 16 LPCC-derived cepstrum coefficients as parametric vectors, the three categories of models gave compatible results. Vector-pair interpolator models yielded best recognition rate. Compared to a VQ-coded reference technique, this model gives close global recognition rate and significatly outperforms for plosive sounds.
Document type :
Complete list of metadata
Contributor : Rapport de Recherche Inria <>
Submitted on : Wednesday, May 24, 2006 - 5:25:41 PM
Last modification on : Thursday, February 11, 2021 - 2:48:31 PM
Long-term archiving on: : Tuesday, April 12, 2011 - 9:09:14 PM


  • HAL Id : inria-00075104, version 1



Yifan Gong, Jean-Paul Haton. Non-linear vector interpolation by neural network for phoneme identification in continuous speech. [Research Report] RR-1457, INRIA. 1991. ⟨inria-00075104⟩



Record views


Files downloads