TY - JOUR AB - In this paper, a novel segmental Hidden Markov Model (HMM) is proposed. The model is based on a modified emission density where additional statistical dependencies between subsequent frames of the speech signal are considered. In the following we derive an effective search strategy for the modified statistical model. Further an approach to parameter reduction is introduced. Experiments were carried out on the AURORA2 database where consistent im AU - Windmann, Stefan AU - Haeb-Umbach, Reinhold AU - Leutnant, Volker ID - 11944 JF - 2008 ITG Conference on Voice Communication (SprachKommunikation) TI - A segmental HMM based on a modified emission probability ER -