Spoken dialog systems

A spoken dialog system is a computer system able to converse with a human with voice. It has two essential components that do not exist in a text dialog system: a speech recognizer and a text-to-speech module. In can be further distinguished from command and control speech systems that can respond to requests but do not attempt to maintain continuity over time.

Components

Varieties of systems

Spoken dialog systems vary in their complexity. Directed dialog systems are very simple and require that the developer create a graph (typically a tree) that manages the task but may not correspond to the needs of the user. Information access systems, typically based on forms, allow users some flexibility (for example in the order in which retrieval constraints are specified, or in the use of optional constraints) but are limited in their capabilities. Problem-solving dialog systems may allow human users to engage in a number of different activities that may include information access, plan construction and possible execution of the latter.

Some examples of systems include:

References

The field of spoken dialog systems is quite large and includes research (featured at scientific conferences such as SIGdial and Interspeech) and a large industrial sector (with its own meetings such as SpeechTek and AVIOS).


The following might provide good technical introductions:

This article is issued from Wikipedia - version of the Thursday, July 02, 2015. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.