Timezone: »

The BUDS POMDP Spoken Dialogue System
Martin Szummer · Matt Henderson · Catherine Breslin · Milica Gasic · Dongho Kim · Blaise Thomson · Pirros Tsiakoulis · Steve Young

Wed Dec 05 07:00 PM -- 11:59 PM (PST) @ Harrah's Special Events Center, 2nd Floor -Tahoe C
Event URL: http://mi.eng.cam.ac.uk/~mh521/nipsdemo12/ »

Bayesian update of dialogue state (BUDS) is a state-of-the art system for human-computer conversation in dialogues. Here, it is employed to build a speech-driven intelligent assistant. The system manages the conversation to help the user achieve their goal as quickly as possible. The main challenge is to converse in a way that overcomes mistakes made by the speech recognizer, or ambiguous utterances by the user. The system can ask for confirmations, pose choices, and ask for additional information, all in order to gain certainty while maximizing dialogue utility.

The system contains a long machine learning pipeline. It preserves a large number of speech recognition hypotheses by representing them as a confusion network (a compact form of an HMM lattice), and applies a semantic decoder directly to this network. The dialogue state is tracked via a Dynamic Belief Network. The system chooses actions according to a policy that has been learned using a POMDP. The ability of the system to maintain uncertainty significantly improves dialogue utility compared to rule-based dialogue systems.

Author Information

Martin Szummer (DeepMind)
Matt Henderson (PolyAI)
Catherine Breslin (University of Cambridge)
Milica Gasic (Heinrich Heine University Düsseldorf)
Dongho Kim (PROWLER.io Limited)
Blaise Thomson (University of Cambridge)
Pirros Tsiakoulis (University of Cambridge)
Steve Young (Cambridge University)

Steve Young is Professor of Information Engineering at Cambridge University and a Senior Member of Technical Staff at Apple. His main research interests lie in the area of statistical spoken language systems including speech recognition, speech synthesis and dialogue management. He is the recipient of a number of awards including an IEEE Signal Processing Society Technical Achievement Award and an IEEE James L Flanagan Speech and Audio Processing Award. He is a Fellow of the IEEE and the UK Royal Academy of Engineering. In addition to his academic career, he has also founded a number of successful start-ups in the speech technology area

More from the Same Authors