DOCTORAL DISSERTATION REFORMULATING HMM AS A TRAJECTORY MODEL BY IMPOSING EXPLICIT RELATIONSHIPS BETWEEN STATIC AND DYNAMIC FEATURES

In recent years, the most popular acoustic model in automatic speech recognition (ASR) and text-to-speech synthesis (TTS) is a hidden Markov model (HMM), due to its ease of implementation and modeling flexibility. However, a number of limitations for modeling sequences of speech spectra using the HMM have been pointed out, such as i) piece-wise constant statistics within a state and ii) conditional independence assumption of state out-put probabilities. To overcome these shortcomings, a variety of alternative acoustic mod-els have been proposed. Although these models can improve model accuracy and speech recognition performance, they generally require an increase in the number of model pa-rameters. In contrast, dynamic features can also enhance performances of HMM-based speech recognizers and has been widely adopted. It can be viewed as a simple mechanism to capture time dependencies in the HMM. However, this approach is mathematically im-proper in the sense of statistical modeling. Generally, the dynamic features are calculated as regression coecients from their neighboring static features. Therefore, relationships between the static and dynamic features are deterministic. However, these relationship