Incremental speech synthesis

Human interaction with spoken dialogue systems differ in many ways from their interactions with each other. One notable example is that spoken dialogue systems tend to have a strict concept of turns which makes the dialogue more similar to a ping-pong game than to humans conversing. Given that we aim at creating spoken dialogue systems that can engage in human-like conversation (note that although this is the case for most dialogue work at KTH, it is not true by necessity; for a discussion see Edlund et al., 2008), this rigid dependence on turns needs a solution. The present paper discusses a step in that direction: the use of incremental varieties of speech synthesis. A brief background and discussion on incrementality in spoken dialogue systems is given, followed by a discussion of the specific requirements an incremental speech synthesis should meet, and a presentation of a prototype system meeting some of these requirements.