Tied triphone semi-Markov model for large vocabulary continuous speech recognition

This paper considers a tied triphone semi-Markov model (SMM) for large vocabulary continuous speech recognition (LVCSR). The semi-Markov model (SMM) can represent statistical dependencies among all the observations within a segment while hidden Markov model (HMM) that is often used for speech recognition assumes only local statistical dependencies between adjacent observations. Especially, this paper focuses on tied triphone construction of SMM for LVCSR. The proposed tied triphone SMM outperformed the HMM in the WSJ speech recognition task.