Combining information sources for confidence estimation with CRF models

Obtaining accurate confidence measures for automatic speech recognition (ASR) transcriptions is an important task which stands to benefit from the use of multiple information sources. This paper investigates the application of conditional random field (CRF) models as a principled technique for combining multiple features from such sources. A novel method for combining suitably defined features is presented, allowing for confidence annotation using lattice-based features of hypotheses other than the lattice 1-best. The resulting framework is applied to different stages of a state-of-the-art large vocabulary speech recognition pipeline, and consistent improvements are shown over a sophisticated baseline system. Copyright © 2011 ISCA.

Using sub-word-level information for confidence estimation with conditional random field models

The task of word-level confidence estimation (CE) for automatic speech recognition (ASR) systems stands to benefit from the combination of suitably defined input features from multiple information sources. However, the information sources of interest may not necessarily operate at the same level of granularity as the underlying ASR system. The research described here builds on previous work on confidence estimation for ASR systems using features extracted from word-level recognition lattices, by incorporating information at the sub-word level. Furthermore, the use of Conditional Random Fields (CRFs) with hidden states is investigated as a technique to combine information for word-level CE. Performance improvements are shown using the sub-word-level information in linear-chain CRFs with appropriately engineered feature functions, as well as when applying the hidden-state CRF model at the word level.

Design for inclusivity: A practical guide to accessible, innovative and user-centred design

Design for Inclusivity is a guide to inclusive design for all types of designers, providing guidelines, real examples and information sources.

Design for Inclusivity

Design for Inclusivity is a guide to inclusive design for all types of designers, providing guidelines, real examples and information sources.

Design, construction and evaluation of systems to predict risk in obstetrics.

We present a systematic, practical approach to developing risk prediction systems, suitable for use with large databases of medical information. An important part of this approach is a novel feature selection algorithm which uses the area under the receiver operating characteristic (ROC) curve to measure the expected discriminative power of different sets of predictor variables. We describe this algorithm and use it to select variables to predict risk of a specific adverse pregnancy outcome: failure to progress in labour. Neural network, logistic regression and hierarchical Bayesian risk prediction models are constructed, all of which achieve close to the limit of performance attainable on this prediction task. We show that better prediction performance requires more discriminative clinical information rather than improved modelling techniques. It is also shown that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy.

Spread transform watermarking for video sources

Spread Transform (ST) is a quantization watermarking algorithm in which vectors of the wavelet coefficients of a host work are quantized, using one of two dithered quantizers, to embed hidden information bits; Loo had some success in applying such a scheme to still images. We extend ST to the video watermarking problem. Visibility considerations require that each spreading vector refer to corresponding pixels in each of several frames, that is, a multi-frame embedding approach. Use of the hierarchical complex wavelet transform (CWT) for a visual mask reduces computation and improves robustness to jitter and valumetric scaling. We present a method of recovering temporal synchronization at the detector, and give initial results demonstrating the robustness and capacity of the scheme.

Data Analysis on Complicated Construction Data Sources: Vision, Research, and Recent Developments

Compared with construction data sources that are usually stored and analyzed in spreadsheets and single data tables, data sources with more complicated structures, such as text documents, site images, web pages, and project schedules have been less intensively studied due to additional challenges in data preparation, representation, and analysis. In this paper, our definition and vision for advanced data analysis addressing such challenges are presented, together with related research results from previous work, as well as our recent developments of data analysis on text-based, image-based, web-based, and network-based construction sources. It is shown in this paper that particular data preparation, representation, and analysis operations should be identified, and integrated with careful problem investigations and scientific validation measures in order to provide general frameworks in support of information search and knowledge discovery from such information-abundant data sources.

Characterising the information requests of aerospace engineering designers

During product development, engineering designers raise several information requests that make them search through human and documentary sources. This paper reports research to characterise, in detail, these requests for designers working in a major aerospace engineering company. The research found that at a high level, a distinction can be made between requests to acquire information and to process information. The former are raised to access design and domain information. The latter, instead, are formed to define designs. For researchers, this study extends existing knowledge of information requests by characterising key differences in their nature and explaining how they are used in the design process. For practitioners, these findings can be used as a basis to understand the diverseness of information requests and how to channel efforts to support designers in information seeking. In particular, the research indicates that a strategy to support designers should enable the development of engineering communities that share information effectively and the introduction of techniques that facilitate the documentation of information. © 2012 Springer-Verlag London Limited.

Novel nanostructured carbon nanotube electron sources

In this chapter, we present a review of our continuing efforts toward the development of discrete, low-dimensional nanostructured carbon-based electron emitters. Carbon nanotubes and nanofibers, herein referred to simply as CNTs, are one-dimensional carbon allotropes formed from cylindrically rolled and nested graphene sheets, have diameters between 1 and 500 nm and lengths of up to several millimeters, and are perfect candidates for field emission (FE) applications. By virtue of their extremely strong sp2 C-C bonding, intrinsic to the graphene hexagonal lattice, CNTs have demonstrated impressive chemical inertness, unprecedented thermal stabilities, significant resistance to electromigration, and exceptionally high axial current carrying capacities, even at elevated temperatures. These near ideal cold cathode electron emitters have incredibly high electric field enhancing aspect ratios combined with virtual point sources of the order of a few nanometers in size. The correct integration and judicious development of suitable FE platforms based on these extraordinary molecules is critical and will ultimately enable enhanced technologies. This chapter will review some of the more recent platforms, devices and structures developed by our group, as well as our contributions towards the development of industry-scalable technologies for ultra-high-resolution electron microscopy, portable x-ray sources, and flexible environmental lighting technologies. © 2012 by Pan Stanford Publishing Pte. Ltd. All rights reserved.