ISCA Archive Eurospeech 1993
ISCA Archive Eurospeech 1993

Grammar learning and word spotting using recurrent neural networks

J. Alvarez-Cercadillo, Luis A. Hernandez-Gomez

An hybrid network system for continuous speech recognition is presented, based in subword units. At the first stage we detect the order, duration and likelihood of the phoneme sequence with a phoneme spotting system based in Hidden Markov Models. At the second level, a Recurrent Neural Network performs the phoneme decoding by selecting the chain of phonemes that forms a legal word. The network was able to learn the underlying phonetic grammar and could reduce the false alarm rates.

Keywords: Continuous Speech Recognition; Hybrid Network; Phoneme Spotting System; Recurrent Neural Network; Grammar learning.