• Publications
  • Influence
The HTK book
The Fundamentals of HTK: General Principles of HMMs, Recognition and Viterbi Decoding, and Continuous Speech Recognition. Expand
The HTK book version 3.4
A Network-based End-to-End Trainable Task-oriented Dialogue System
This work introduces a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework that can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain. Expand
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
A statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure that can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates. Expand
Neural Belief Tracker: Data-Driven Dialogue State Tracking
This work proposes a novel Neural Belief Tracking (NBT) framework which overcomes past limitations, matching the performance of state-of-the-art models which rely on hand-crafted semantic lexicons and outperforming them when such lexicons are not provided. Expand
Applications of stochastic context-free grammars using the Inside-Outside algorithm
Two applications in speech recognition of the use of stochastic context-free grammars trained automatically via the Inside-Outside Algorithm, used to model VQ encoded speech for isolated word recognition and compared directly to HMMs used for the same task are described. Expand
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management
This paper explains how Partially Observable Markov Decision Processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialogue systems and describes a form of approximation called the Hidden Information State model which does scale and which can be used to build practical systems. Expand
The Application of Hidden Markov Models in Speech Recognition
The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then to describe the various refinements which are needed to achieve state-of-the-art performance. Expand
Word-Based Dialog State Tracking with Recurrent Neural Networks
A new wordbased tracking method which maps directly from the speech recognition results to the dialog state without using an explicit semantic decoder is presented, based on a recurrent neural network structure which is capable of generalising to unseen dialog state hypotheses, and which requires very little feature engineering. Expand
Partially observable Markov decision processes for spoken dialog systems
This paper cast a spoken dialog system as a partially observable Markov decision process (POMDP) and shows how this formulation unifies and extends existing techniques to form a single principled framework. Expand