Development of the 2003 CU-HTK conversational telephone speech transcription system

This paper describes the development of the 2003 CU-HTK large vocabulary speech recognition system for Conversational Telephone Speech (CTS). The system was designed based on a multi-pass, multi-branch structure where the output of all branches is combined using system combination. A number of advanced modelling techniques such as Speaker Adaptive Training, Heteroscedastic Linear Discriminant Analysis, Minimum Phone Error estimation and specially constructed Single Pronunciation dictionaries were employed. The effectiveness of each of these techniques and their potential contribution to the result of system combination was evaluated in the framework of a state-of-the-art LVCSR system with sophisticated adaptation. The final 2003 CU-HTK CTS system constructed from some of these models is described and its performance on the DARPA/NIST 2003 Rich Transcription (RT-03) evaluation test set is discussed.

Simulation-based optimal sensor scheduling with application to observer trajectory planning

The sensor scheduling problem can be formulated as a controlled hidden Markov model and this paper solves the problem when the state, observation and action spaces are continuous. This general case is important as it is the natural framework for many applications. The aim is to minimise the variance of the estimation error of the hidden state w.r.t. the action sequence. We present a novel simulation-based method that uses a stochastic gradient algorithm to find optimal actions. © 2007 Elsevier Ltd. All rights reserved.

The CU-HTK Mandarin broadcast news transcription system

This paper discusses the development of the CU-HTK Mandarin Broadcast News (BN) transcription system. The Mandarin BN task includes a significant amount of English data. Hence techniques have been investigated to allow the same system to handle both Mandarin and English by augmenting the Mandarin training sets with English acoustic and language model training data. A range of acoustic models were built including models based on Gaussianised features, speaker adaptive training and feature-space MPE. A multi-branch system architecture is described in which multiple acoustic model types, alternate phone sets and segmentations can be used in a system combination framework to generate the final output. The final system shows state-of-the-art performance over a range of test sets. ©2006 British Crown Copyright.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. In normal cross adaptation it is assumed that useful diversity among systems exists only at acoustic level. However, complimentary features among complex LVCSR systems also manifest themselves in other layers of modelling hierarchy, e.g., subword and word level. It is thus interesting to also cross adapt language models (LM) to capture them. In this paper cross adaptation of multi-level LMs modelling both syllable and word sequences was investigated to improve LVCSR system combination. Significant error rate gains up to 6.7% rel. were obtained over ROVER and acoustic model only cross adaptation when combining 13 Chinese LVCSR subsystems used in the 2010 DARPA GALE evaluation. © 2010 ISCA.

An overview of sequential Monte Carlo methods for parameter estimation in general state-space models

Nonlinear non-Gaussian state-space models arise in numerous applications in control and signal processing. Sequential Monte Carlo (SMC) methods, also known as Particle Filters, are numerical techniques based on Importance Sampling for solving the optimal state estimation problem. The task of calibrating the state-space model is an important problem frequently faced by practitioners and the observed data may be used to estimate the parameters of the model. The aim of this paper is to present a comprehensive overview of SMC methods that have been proposed for this task accompanied with a discussion of their advantages and limitations.

An experimental semi-active anti-roll system

The use of anti-roll bars to provide additional roll stiffness and therefore to reduce the trade-off between ride and rollover performance has previously been studied. However, little work has been carried out to investigate the benefits of a switchable roll stiffness. Such a semi-active anti-roll system has the ability to have a low roll stiffness during straight-ahead driving for improved ride performance and high roll stiffness during cornering for improved roll performance. Modelling of such a system is conducted and the model is validated against a semi-active anti-roll system fitted to an experimental vehicle. Experimental and theoretical investigations are used to investigate the performance of such a system with several different strategies employed to switch to the high-stiffness state. The use of an air suspension on the vehicle to roll into corners is also investigated, as is the possibility of exploiting the road layout by allowing the vehicle to be in a low-roll-stiffness configuration during a corner, and then to switch to the high-roll-stiffness configuration midcorner, hence 'locking in' a roll angle. The best rollover performance improvement that was achieved was 12.5 per cent. © IMechE 2008.

Bayesian dialogue system for the let's go spoken dialogue challenge

This paper describes how Bayesian updates of dialogue state can be used to build a bus information spoken dialogue system. The resulting system was deployed as part of the 2010 Spoken Dialogue Challenge. The purpose of this paper is to describe the system, and provide both simulated and human evaluations of its performance. In control tests by human users, the success rate of the system was 24.5% higher than the baseline Lets Go! system. ©2010 IEEE.

Diesel Cylinder Charge Properties: Feed-Forward Control and Cycle-by-Cycle Analysis Using an In-Cylinder Gas Sampling System

Common-rail fuel injection systems on modern light duty diesel engines are effectively able to respond instantaneously to changes in the demanded injection quantity. In contrast, the air-system is subject to significantly slower dynamics, primarily due to filling/emptying effects in the manifolds and turbocharger inertia. The behaviour of the air-path in a diesel engine is therefore the main limiting factor in terms of engine-out emissions during transient operation. This paper presents a simple mean-value model for the air-path during throttled operation, which is used to design a feed-forward controller that delivers very rapid changes in the in-cylinder charge properties. The feed-forward control action is validated using a state-of-the-art sampling system that allows true cycle-by-cycle measurement of the in-cylinder CO2 concentration. © 2011 SAE International.