The HTK book
The Fundamentals of HTK: General Principles of HMMs, Recognition and Viterbi Decoding, and Continuous Speech Recognition.
A Network-based End-to-End Trainable Task-oriented Dialogue System
- L. Rojas-Barahona, M. Gašić, David Vandyke
- Computer ScienceConference of the European Chapter of the…
- 15 April 2016
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.
The HTK book version 3.4
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
- Tsung-Hsien Wen, Milica Gasic, N. Mrksic, Pei-hao Su, David Vandyke, S. Young
- Computer ScienceConference on Empirical Methods in Natural…
- 7 August 2015
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.
Neural Belief Tracker: Data-Driven Dialogue State Tracking
- N. Mrksic, Diarmuid Ó Séaghdha, Tsung-Hsien Wen, Blaise Thomson, S. Young
- Computer ScienceAnnual Meeting of the Association for…
- 12 June 2016
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.
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.
Phone-level pronunciation scoring and assessment for interactive language learning
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.
Applications of stochastic context-free grammars using the Inside-Outside algorithm