Context-dependent Modeling in a Segment-based Speech Recognition System

The goal of this thesis is to explore various strategies for incorporating contextual information into a segment-based speech recognition system, while maintaining com-putational costs at a level acceptable for implementation in a real-time system. The latter is achieved by using context-independent models in the search, while context-dependent models are reserved for re-scoring the hypotheses proposed by the context-independent system. Within this framework, several types of context-dependent sub-word units were evaluated, including word-dependent, biphone, and triphone units. In each case, deleted interpolation was used to compensate for the lack of training data for the mod-els. Other types of context-dependent modeling, such as context-dependent boundary modeling and "offset " modeling, were also used successfully in the re-scoring pass. The evaluation of the system was performed using the Resource Management task. Context-dependent segment models were able to reduce the error rate of the context-independent system by more than twenty percent, and context-dependen