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.

Multi-fidelity simulation modelling in optimization of a hybrid submarine propulsion system

Multi-objective Genetic Algorithms have become a popular choice to aid in optimising the size of the whole hybrid power train. Within these optimisation processes, other optimisation techniques for the control strategy are implemented. This optimisation within an optimisation requires many simulations to be run, so reducing the computational cost is highly desired. This paper presents an optimisation framework consisting of a series hybrid optimisation algorithm, in which a global search optimizes a submarine propulsion system using low-fidelity models and, in order to refine the results, a local search is used with high-fidelity models. The effectiveness of the Hybrid optimisation algorithm is demonstrated with the optimisation of a submarine propulsion system. © 2011 EPE Association - European Power Electr.

The influence of turbine stator well coolant flow rate and passage configuration on cooling effectiveness

Market competitiveness for aero engine power plant dictates that improvements in engine performance and reliability are guaranteed a priori by manufacturers. The requirement to accurately predict the life of engine components makes exacting demands of the internal air system, which must provide effective cooling over the engine duty cycle with the minimum consumption of compressor section air. Tests have been conducted at the University of Sussex using a turbine test facility which comprises a two stage turbine with an individual stage pressure ratio of 1.7:1. Main annulus air is supplied by an adapted Rolls-Royce Dart compressor at up to 440 K and 4.8 kg s-1. Cooling flow rates ranging from 0.71 to 1.46 Cw, ent, a disc entrainment parameter, have been used to allow ingress or egress dominated stator well flow conditions. The mechanical design of the test section allows internal cooling geometry to be rapidly re-configured, allowing the effect of jet momentum and coolant trajectory to be investigated. An important facet to this investigation is the use of CFD to model and analyse the flow structures associated with the cavity conditions tested, as well as to inform the design of cooling path geometry. This paper reports on the effectiveness of stator well coolant flow rate and delivery configurations using experimental data and also CFD analysis to better quantify the effect of stator well flow distribution on component temperatures. Copyright © 2011 by Rolls-Royce plc.