Components of a Spoken Dialogue System — Speech Input and Output
A spoken dialogue system consists of a number of components that need to work together for the system to function successfully. Spoken dialogue toolkits provide integrated environments in which some of the components, such as the speech recognition and the text-to-speech (TTS) engines, are built-in. Other components, such as the dialogue manager, will generally require more effort to develop. This chapter presents an overview of the components that are concerned with processing the user’s input to the system and the system’s output to the user — speech recognition, language understanding, language generation and speech output. The central component of a spoken dialogue system, the dialogue manager, will be described in Chapter 5.
KeywordsSpeech Recognition Noun Phrase Acoustic Model Language Generation Speech Recognition System
Unable to display preview. Download preview PDF.