This report presents uncertainty decoding as a method for robust automatic speech recognition for the Noise Robust Automatic Speech Recognition project funded by Toshiba Research Europe Limited. The effects of noise on speech recognition are reviewed and a general framework for noise robust speech recognition introduced. Common and related noise robustness techniques are described in the contex...

Uncertainty quantification (UQ) has been achieved for the first time on the self-noise prediction of a low-subsonic axial fan. Realistic 5% and 4% errors are introduced on the volume flow-rate and the rotational speed, respectively, and a set of 81 ReynoldsAveraged Navier-Stokes (RANS) simulations of the fan mounted on an axisymmetric test plenum has been simulated at Clenshaw-Curtis points. By...

For climate change projections to be useful, the magnitude of change must be understood relative to the magnitude of uncertainty in model predictions. We quantified the signal-to-noise ratio in projected distributional responses of boreal birds to climate change, and compared sources of uncertainty. Boosted regression tree models of abundance were generated for 80 boreal-breeding bird species u...

In general, estimates of uncertainties in measured values give an idea of the quality of the measurement. However with environmental noise measurements this is not necessarily the case since the variables affecting the measured levels can often not be controlled. Consequently an appreciation of the uncertainties in results lead rather to a better understanding of the measurement and its potenti...

Declaration This dissertation is the result of my own work and includes nothing which is the outcome of work done in collaboration. It has not been submitted in whole or in part for a degree at any other university. Some of the work has been published previously in conference proceedings [93, 94, 95] and technical reports [90, 91, 92]. The length of this thesis including appendices, references,...

Learning against label noise is a vital topic to guarantee reliable performance for deep neural networks.Recent research usually refers dynamic modeling with model output probabilities and loss values, then separates clean noisy samples.These methods have gained notable success. However, unlike cherry-picked data, existing approaches often cannot perform well when facing imbalanced datasets, co...

This paper examines reasoning under uncertainty in the case where the AI reasoning mechanism is itself subject to random error or noise in its own processes. The main result is a demonstration that systematic, directed biases naturally arise if there is random noise in a reasoning process that follows the normative rules of probability theory. A number of reliable errors in human reasoning unde...

Background noise can have a significant impact on the performance of speech recognition systems. A range of fast featurespace and model-based schemes have been investigated to increase robustness. Model-based approaches typically achieve lower error rates, but at an increased computational load compared to feature-based approaches. Thismakes their use inmany situations impractical. The uncertai...