Testing of Depth-Encoded Hough Voting for Infrastructure Object Detection

The lack of viable methods to map and label existing infrastructure is one of the engineering grand challenges for the 21st century. For instance, over two thirds of the effort needed to geometrically model even simple infrastructure is spent on manually converting a cloud of points to a 3D model. The result is that few facilities today have a complete record of as-built information and that as-built models are not produced for the vast majority of new construction and retrofit projects. This leads to rework and design changes that can cost up to 10% of the installed costs. Automatically detecting building components could address this challenge. However, existing methods for detecting building components are not view and scale-invariant, or have only been validated in restricted scenarios that require a priori knowledge without considering occlusions. This leads to their constrained applicability in complex civil infrastructure scenes. In this paper, we test a pose-invariant method of labeling existing infrastructure. This method simultaneously detects objects and estimates their poses. It takes advantage of a recent novel formulation for object detection and customizes it to generic civil infrastructure scenes. Our preliminary experiments demonstrate that this method achieves convincing recognition results.

Improving LVCSR system combination using neural network language model cross adaptation

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. The standard approach involves only cross adapting acoustic models. To fully exploit the complimentary features among sub-systems, language model (LM) cross adaptation techniques can be used. Previous research on multi-level n-gram LM cross adaptation is extended to further include the cross adaptation of neural network LMs in this paper. Using this improved LM cross adaptation framework, significant error rate gains of 4.0%-7.1% relative were obtained over acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. Copyright © 2011 ISCA.

Use of contexts in language model interpolation and adaptation

Language models (LMs) are often constructed by building multiple individual component models that are combined using context independent interpolation weights. By tuning these weights, using either perplexity or discriminative approaches, it is possible to adapt LMs to a particular task. This paper investigates the use of context dependent weighting in both interpolation and test-time adaptation of language models. Depending on the previous word contexts, a discrete history weighting function is used to adjust the contribution from each component model. As this dramatically increases the number of parameters to estimate, robust weight estimation schemes are required. Several approaches are described in this paper. The first approach is based on MAP estimation where interpolation weights of lower order contexts are used as smoothing priors. The second approach uses training data to ensure robust estimation of LM interpolation weights. This can also serve as a smoothing prior for MAP adaptation. A normalized perplexity metric is proposed to handle the bias of the standard perplexity criterion to corpus size. A range of schemes to combine weight information obtained from training data and test data hypotheses are also proposed to improve robustness during context dependent LM adaptation. In addition, a minimum Bayes' risk (MBR) based discriminative training scheme is also proposed. An efficient weighted finite state transducer (WFST) decoding algorithm for context dependent interpolation is also presented. The proposed technique was evaluated using a state-of-the-art Mandarin Chinese broadcast speech transcription task. Character error rate (CER) reductions up to 7.3 relative were obtained as well as consistent perplexity improvements. © 2012 Elsevier Ltd. All rights reserved.

UK-NEES - Distributed hybrid testing between Bristol, Cambridge and Oxford Universities: Connecting structural dynamics labs to a geotechnical centrifuge

Distributed hybrid testing is a natural extension to and builds upon the local hybrid testing technique. Taking advantage of the hybrid nature of the test, it allows a sharing of resources and expertise between researchers from different disciplines by connecting multiple geographically distributed sites for joint testing. As part of the UK-NEES project, a successful series of three-site distributed hybrid tests have been carried out between Bristol, Cambridge and Oxford Universities. The first known multi-site distributed hybrid tests in the UK, they connected via a dedicated fibre network, using custom software, the geotechnical centrifuge at Cambridge to structural components at Bristol and Oxford. These experiments were to prove the connection and useful insights were gained into the issues involved with this distributed environment. A wider aim is towards providing a flexible testing framework to facilitate multi-disciplinary experiments such as the accurate investigation of the influence of foundations on structural systems under seismic and other loading. Time scaling incompatibilities mean true seismic soil structure interaction using a centrifuge at g is not possible, though it is clear that distributed centrifuge testing can be valuable in other problems. Development is continuing to overcome the issues encountered, in order to improve future distributed tests in the UK and beyond.

Flaw sizing in pipes using long-range guided wave testing

The absence of adequate inspection data from difficult-to-access areas on pipelines, such as cased-road crossings, makes determination of fitness for continued service and compliance with increasingly stringent regulatory requirements problematic. Screening for corrosion using long-range guided wave testing is a relatively new inspection technique. The complexity of the possible modes of vibration means the technique can be difficult to implement effectively but this also means that it has great potential for both detecting and characterizing flaws. The ability to determine flaw size would enable the direct application of standard procedures for determining fitness-for-service, such as ASME B31G, RSTRENG, or equivalent for tens of metres of pipeline from a single inspection location. This paper presents a new technique for flaw sizing using guided wave inspection data. The technique has been developed using finite element models and experimentally validated on 6'' Schedule 40 steel pipe. Some basic fitness-for-service assessments have been carried out using the measured values and the maximum allowable operating pressure was accurately determined. © 2011 American Institute of Physics.

Syllable language models for Mandarin speech recognition: exploiting character language models.

Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.

Design and testing of a 250 kW medium-speed Brushless DFIG

This paper presents the design and testing of a 250 kW medium-speed Brushless Doubly-Fed Induction Generator (Brushless DFIG), and its associated power electronics and control systems. The experimental tests confirm the design, and show the system's steady-state and dynamic performance. The medium-speed Brushless DFIG in combination with a simplified two-stage gearbox promises a low-cost low-maintenance and reliable drive train for wind turbine applications.

Half-bridge SIC inverter for hybrid electric vehicles: Design, development and testing at higher operating temperature

In recent years, Silicon Carbide (SiC) semiconductor devices have shown promise for high density power electronic applications, due to their electrical and thermal properties. In this paper, the performance of SiC JFETs for hybrid electric vehicle (HEV) applications is investigated at heatsink temperatures of 100 °C. The thermal runaway characteristics, maximum current density and packaging temperature limitations of the devices are considered and the efficiency implications discussed. To quantify the power density capabilities of power transistors, a novel 'expression of rating' (EoR) is proposed. A prototype single phase, half-bridge voltage source inverter using SiC JFETs is also tested and its performance at 25 °C and 100 °C investigated.

Discriminative spoken language understanding using word confusion networks

Current commercial dialogue systems typically use hand-crafted grammars for Spoken Language Understanding (SLU) operating on the top one or two hypotheses output by the speech recogniser. These systems are expensive to develop and they suffer from significant degradation in performance when faced with recognition errors. This paper presents a robust method for SLU based on features extracted from the full posterior distribution of recognition hypotheses encoded in the form of word confusion networks. Following [1], the system uses SVM classifiers operating on n-gram features, trained on unaligned input/output pairs. Performance is evaluated on both an off-line corpus and on-line in a live user trial. It is shown that a statistical discriminative approach to SLU operating on the full posterior ASR output distribution can substantially improve performance both in terms of accuracy and overall dialogue reward. Furthermore, additional gains can be obtained by incorporating features from the previous system output. © 2012 IEEE.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple sub-systems that may even be developed at different sites. Cross system adaptation, in which model adaptation is performed using the outputs from another sub-system, can be used as an alternative to hypothesis level combination schemes such as ROVER. Normally cross adaptation is only performed on the acoustic models. However, there are many other levels in LVCSR systems' modelling hierarchy where complimentary features may be exploited, for example, the sub-word and the word level, to further improve cross adaptation based system combination. It is thus interesting to also cross adapt language models (LMs) to capture these additional useful features. In this paper cross adaptation is applied to three forms of language models, a multi-level LM that models both syllable and word sequences, a word level neural network LM, and the linear combination of the two. Significant error rate reductions of 4.0-7.1% relative were obtained over ROVER and acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. © 2012 Elsevier Ltd. All rights reserved.

Design and testing of an ortho-planar micro-valve

This paper presents the production and testing of an ortho-planar one-way micro-valve. The main advantages of such valves are that they are very compact and can be made from a single flat piece of material. A previous paper presents and discusses a micro-valve assembly based on a spider spring. The present paper focuses on the valve assembly process and the valve performance.. Several prototypes with a bore of 0.2 mm have been built using two manufacturing techniques (μEDM and stereo-lithography) and tested for pressures up to 7 bars. © 2008 International Federation for Information Processing.