Sciweavers

NOLISP
2007
Springer

Word Recognition with a Hierarchical Neural Network

13 years 9 months ago
Word Recognition with a Hierarchical Neural Network
In this paper we propose a feedforward neural network for syllable recognition. The core of the recognition system is based on a hierarchical architecture initially developed for visual object recognition. We show that, given the similarities between the primary auditory and visual cortexes, such a system can successfully be used for speech recognition. Syllables are used as basic units for the recognition. Their spectrograms, computed using a Gammatone filterbank, are interpreted as images and subsequently feed into the neural network after a preprocessing step that enhances the formant frequencies and normalizes the length of the syllables. The performance of our system has been analyzed on the recognition of 25 different monosyllabic words. The parameters of the architecture have been optimized using an evolutionary strategy. Compared to the Sphinx-4 speech recognition system, our system achieves better robustness and generalization capabilities in noisy conditions.
Xavier Domont, Martin Heckmann, Heiko Wersing, Fra
Added 08 Jun 2010
Updated 08 Jun 2010
Type Conference
Year 2007
Where NOLISP
Authors Xavier Domont, Martin Heckmann, Heiko Wersing, Frank Joublin, Stefan Menzel, Bernhard Sendhoff, Christian Goerick
Comments (0)