A Hybrid Neural Net System for State-of-the-Art Continuous Speech Recognition
Zavaliagkos, G., Zhao, Y., Schwartz, R., Makhoul, J.
–Neural Information Processing Systems
Untill recently, state-of-the-art, large-vocabulary, continuous speech recognition (CSR) has employed Hidden Markov Modeling (HMM) to model speech sounds. In an attempt to improve over HMM we developed a hybrid system that integrates HMM technology with neural We present the concept of a "Segmental Neural Net"networks.
Neural Information Processing Systems
Dec-31-1993