Phoneme Identification in Continuous Speech
Yifan Gong, Jean‐Paul Haton · 1991
The correlations 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 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 phonemic 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 continuous speech under phoneme spotting test using 16 LPCC-derived cepstrum coefficients as parametric vectors, the three categories of models gave compatible results. uecfor-pair interpolator models yield best recognition rate. Compared to a VQ-coded reference comparison technique, this model gives close global recognition rate and significantly outperforms for plosive sounds.