 |
Method and Tool Innovations for Speech Science Education (M.A.T.I.S.S.E.)April 16-17, 1999 |
 |
|
Method and Tool Innovations for Speech Science Education (M.A.T.I.S.S.E.)April 16-17, 1999 |
|
Spoken language interaction with computers has become a practical possibility as a result of recent technological developments in the speech sciences. The development of a spoken dialogue system is a complex process involving the integration of the various components of spoken language technology, including speech recognition, natural language processing, dialogue modelling, and speech synthesis. Various toolkits and authoring environments have been produced that provide assistance with this process. This paper reports on the use of CSLU’s RAD (Rapid Application Developer) to provide practical experience for undergraduate students in the specification and development of spoken dialogue systems. Students of linguistics and speech and language therapy were able to develop simple state-based dialogues as well as sub-dialogues and repair dialogues as well as creating their own pronunciation models of the words to be recognised by simply altering the automatically generated Worldbet labels or by using the visualisation tools provided with the toolkit. Students with a computing background were able to develop more complex interactions with external data as well as more complex dialogue models. The paper reports on recent additions to the toolkit that enable robust parsing of the input as well as more flexible dialogue management.
Bibliographic reference. McTear, Michael F. (1999): "Using the CSLU toolkit for practicals in spoken dialogue technology ", In MATISSE-1999, 113-116.