AG 1, AG 2, AG 3, AG 4, AG 5, RG1, SWS, MMCI   Info

Public Audience

English

60 Minutes

Saarbrücken

Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have innumerable benefits. By using speech as a medium, a computer interface can facilitate swift, human-like acquisition of information. In recent years, systems with speech interfaces have become ever more popular, as is evident from the rise of personal assistants such as Siri, Google Home, Cortana or Amazon Alexa. The main problems however are that these systems do not learn from their users, that they require a designer to manually extend their behaviour, and that, once built for one domain, they cannot be reused for another domain. In this lecture, I will show how machine learning methods based on Gaussian processes can be used to tackle each of these problems.

The final part of the lecture will look ahead towards the next generation of spoken dialogue systems. These systems will need to operate on large and dynamic domains and, more importantly, be capable of conducting rich and natural interaction. I will present a research roadmap towards this goal and illustrate the need for such research with a potential application in mental health.

Connie Balzert

--email hidden

passcode not visible

logged in users only