Part of Advances in Neural Information Processing Systems 5 (NIPS 1992)
G. Zavaliagkos, Y. Zhao, R. Schwartz, J. Makhoul
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 neu(cid:173) ral networks. We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in CSR. By taking into account all the frames of a phonetic segment simultaneously, the SNN overcomes the well-known conditional-independence limitation of HMMs. In several speaker-independent experiments with the DARPA Resource Manage(cid:173) ment corpus, the hybrid system showed a consistent improvement in performance over the baseline HMM system.