Speech Processing

Speech Processing research include Automatic Speech Recognition, Text To Speech (aka, Speech Synthesis), Spoken Language Understanding, Dialogue Management, and Natural Language Generation. The range of applications is not limited. Combining all these independent modules will lead to the development of a spoken dialogue system. A well-known approach to dialogue system architecture is to build it as a chain of processes (i.e., a pipeline), where the system takes a user speech as input and generates a system utterance as output.