The effect of language models on phonetic decoding for spoken term detection

Spoken term detection (STD) popularly involves performing word or sub-word level speech recognition and indexing the result. This work challenges the assumption that improved speech recognition accuracy implies better indexing for STD. Using an index derived from phone lattices, this paper examines the effect of language model selection on the relationship between phone recognition accuracy and STD accuracy. Results suggest that language models usually improve phone recognition accuracy but their inclusion does not always translate to improved STD accuracy. The findings suggest that using phone recognition accuracy to measure the quality of an STD index can be problematic, and highlight the need for an alternative that is more closely aligned with the goals of the specific detection task.

Spoken term detection using fast phonetic decoding

While spoken term detection (STD) systems based on word indices provide good accuracy, there are several practical applications where it is infeasible or too costly to employ an LVCSR engine. An STD system is presented, which is designed to incorporate a fast phonetic decoding front-end and be robust to decoding errors whilst still allowing for rapid search speeds. This goal is achieved through mono-phone open-loop decoding coupled with fast hierarchical phone lattice search. Results demonstrate that an STD system that is designed with the constraint of a fast and simple phonetic decoding front-end requires a compromise to be made between search speed and search accuracy.

Experimenting with an intrusion detection system for encrypted networks

Network-based Intrusion Detection Systems (NIDSs) analyse network traffic to detect instances of malicious activity. Typically, this is only possible when the network traffic is accessible for analysis. With the growing use of Virtual Private Networks (VPNs) that encrypt network traffic, the NIDS can no longer access this crucial audit data. In this paper, we present an implementation and evaluation of our approach proposed in Goh et al. (2009). It is based on Shamir's secret-sharing scheme and allows a NIDS to function normally in a VPN without any modifications and without compromising the confidentiality afforded by the VPN.

Towards an automatic road lane marks extraction based on ISODATA segmentation and shadow detection from large-scale aerial images

The automatic extraction of road features from remote sensed images has been a topic of great interest within the photogrammetric and remote sensing communities for over 3 decades. Although various techniques have been reported in the literature, it is still challenging to efficiently extract the road details with the increasing of image resolution as well as the requirement for accurate and up-to-date road data. In this paper, we will focus on the automatic detection of road lane markings, which are crucial for many applications, including lane level navigation and lane departure warning. The approach consists of four steps: i) data preprocessing, ii) image segmentation and road surface detection, iii) road lane marking extraction based on the generated road surface, and iv) testing and system evaluation. The proposed approach utilized the unsupervised ISODATA image segmentation algorithm, which segments the image into vegetation regions, and road surface based only on the Cb component of YCbCr color space. A shadow detection method based on YCbCr color space is also employed to detect and recover the shadows from the road surface casted by the vehicles and trees. Finally, the lane marking features are detected from the road surface using the histogram clustering. The experiments of applying the proposed method to the aerial imagery dataset of Gympie, Queensland demonstrate the efficiency of the approach.

Damage assessment of 3D reinforced concrete frame under external explosion loading

Multi-storey buildings are highly vulnerable to terrorist bombing attacks in various parts of the world. Large numbers of casualties and extensive property damage result not only from blast overpressure, but also from the failing of structural components. Understanding the blast response and damage consequences of reinforced concrete (RC) building frames is therefore important when assessing multi-storey buildings designed to resist normal gravity loads. However, limited research has been conducted to identify the blast response and damage of RC frames in order to assess the vulnerability of entire buildings. This paper discusses the blast response and evaluation of damage of three-dimension (3D) RC rigid frame under potential blast loads scenarios. The explicit finite element modelling and analysis under time history blast pressure loads were carried out by LS DYNA code. Complete 3D RC frame was developed with relevant reinforcement details and material models with strain rate effect. Idealised triangular blast pressures calculated from standard manuals are applied on the front face of the model in the present investigation. The analysis results show the blast response, as displacements and material yielding of the structural elements in the RC frame. The level of damage is evaluated and classified according to the selected load case scenarios. Residual load carrying capacities are evaluated and level of damage was presented by the defined damage indices. This information is necessary to determine the vulnerability of existing multi-storey buildings with RC frames and to identify the level of damage under typical external explosion environments. It also provides basic guidance to the design of new buildings to resist blast loads.

Structural health monitoring of bridges using acoustic emission technology

Bridges are an important part of society's infrastructure and reliable methods are necessary to monitor them and ensure their safety and efficiency. Bridges deteriorate with age and early detection of damage helps in prolonging the lives and prevent catastrophic failures. Most bridges still in used today were built decades ago and are now subjected to changes in load patterns, which can cause localized distress and if not corrected can result in bridge failure. In the past, monitoring of structures was usually done by means of visual inspection and tapping of the structures using a small hammer. Recent advancements of sensors and information technologies have resulted in new ways of monitoring the performance of structures. This paper briefly describes the current technologies used in bridge structures condition monitoring with its prime focus in the application of acoustic emission (AE) technology in the monitoring of bridge structures and its challenges.