Professor Steve Young, Projects


	Steve Young

Current and Recent Projects

Parlance: Tools for Ambient Linguistic Knowledge
This is a collaborative project that aims to design and build mobile applications that approach human performance in conversational interaction. The project involves developing an architecture to support incremental dialogue, and advancing statistical approaches to allow dialogues to adapt and extend to new domains. (Parlance Project Website)
Sponsor:	EU FP7: STREP
Robust Dialogue for Infotainment
The goal of this project is to develop techniques and tools which will enable information services to be provided in-car using natural spoken language [ie not keywords or prescribed commands] as the primary input/output modality. The approach is based on a novel statistical framework called the Partially Observable Markov Decision Process (POMDP). The key benefit of the approach is that for a given level of recognition accuracy, a POMDP-based dialogue manager can provide increased tolerance to errors and a more natural user-oriented dialogue. The research results will be demonstrated by a proof-of-concept server-based implementation of an in-car tourist information service which will demonstrate both a habitable dialogue and significantly improved robustness compared to existing spoken dialogue technology.
Sponsor:	General Motors

ATK/HTK: Real-Time HMM Toolkit for Spoken Dialogue Systems
This is a project to develop a set of freely available C++ wrappers to allow speech recognition systems developed using HTK . to be easily integrated into real-time spoken dialogue systems. (More)
Sponsor:	Cambridge University

CLASSIC: Tools for Ambient Linguistic Knowledge
This is a collaborative project to investigate end-end statistical approaches to building spoken dialogue systems, and in particular the use of reinforcement learning and partially observable MDPs for modelling the dialogue management component of such systems. (Classic Project Website)
Sponsor:	EU FP7: STREP

Spoken Dialogue Management using Partially Observable Markov Decision Processes
This project aims to develop a specific implementation strategy for POMDP-based spoken dialogue systems called the Hidden Information State (HIS) system. In this approach, dialogue states are grouped into partitions and represented by collections of branching trees. The work focuses on the efficient manipulation of these tries, probability models and efficient policy optimisation. (Project Website)
Sponsor:	EPSRC EP/F013930/1