Non-linear vector interpolation by neural network for phoneme identification in continuous speech - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1991

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

Yifan Gong
  • Function : Author
Jean-Paul Haton
  • Function : Author
  • PersonId : 830987

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.

Domains

Other [cs.OH]
Fichier principal
Vignette du fichier
RR-1457.pdf (721.91 Ko) Télécharger le fichier

Dates and versions

inria-00075104 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00075104 , version 1

Cite

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⟩
81 View
94 Download

Share

Gmail Facebook X LinkedIn More