SPEECH RECOGNITION IN VODIS II.

VODIS II, a research system in which recognition is based on the conventional one-pass connected-word algorithm extended in two ways, is described. Syntactic constraints can now be applied directly via context-free-grammar rules, and the algorithm generates a lattice of candidate word matches rather than a single globally optimal sequence. This lattice is then processed by a chart parser and an intelligent dialogue controller to obtain the most plausible interpretations of the input. A key feature of the VODIS II architecture is that the concept of an abstract word model allows the system to be used with different pattern-matching technologies and hardware. The current system implements the word models on a real-time dynamic-time-warping recognizer.

The modified Kanerva model for automatic speech recognition

A parallel processing network derived from Kanerva's associative memory theory Kanerva 1984 is shown to be able to train rapidly on connected speech data and recognize further speech data with a label error rate of 0·68%. This modified Kanerva model can be trained substantially faster than other networks with comparable pattern discrimination properties. Kanerva presented his theory of a self-propagating search in 1984, and showed theoretically that large-scale versions of his model would have powerful pattern matching properties. This paper describes how the design for the modified Kanerva model is derived from Kanerva's original theory. Several designs are tested to discover which form may be implemented fastest while still maintaining versatile recognition performance. A method is developed to deal with the time varying nature of the speech signal by recognizing static patterns together with a fixed quantity of contextual information. In order to recognize speech features in different contexts it is necessary for a network to be able to model disjoint pattern classes. This type of modelling cannot be performed by a single layer of links. Network research was once held back by the inability of single-layer networks to solve this sort of problem, and the lack of a training algorithm for multi-layer networks. Rumelhart, Hinton & Williams 1985 provided one solution by demonstrating the "back propagation" training algorithm for multi-layer networks. A second alternative is used in the modified Kanerva model. A non-linear fixed transformation maps the pattern space into a space of higher dimensionality in which the speech features are linearly separable. A single-layer network may then be used to perform the recognition. The advantage of this solution over the other using multi-layer networks lies in the greater power and speed of the single-layer network training algorithm. © 1989.

Practical matching of principal stress field geometries in composite components

A simple composite design methodology has been developed from the basic principles of composite component failure. This design approach applies the principles of stress field matching to develop suitable reinforcement patterns around three-dimensional details such as lugs in mechanical components. The resulting patterns are essentially curvilinear orthogonal meshes, adjusted to meet the restrictions imposed by geometric restraints and the intended manufacturing process. Whilst the principles behind the design methodology can be applied to components produced by differing manufacturing processes, the results found from looking at simple generic example problems suggest a realistic and practical generic manufacturing approach. The underlying principles of the design methodology are described and simple analyses are used to help illustrate both the methodology and how such components behave. These analyses suggest it is possible to replace high-strength steel lugs with composite components whose strength-to-weight ratio is some 4-5 times better. © 1998 Elsevier Science Ltd. All rights reserved.

New tools for self-organised pattern formation

Position-dependent gene expression is a critical aspect of the development and behaviour of multicellular organisms. It requires a complex series of interactions to occur between different cell types in addition to intracellular signalling cascades. We used Escherichia coli to study the properties of an artificial signalling system at the interface between two expanding cell populations. We genetically engineered one population to produce a diffusible acyl-homoserine lactone (AHL) signal, and another population to respond to it. Our experiments demonstrate how such a signal can be used to reproducibly generate simple visible patterns with high accuracy in swimming agar. The producing and responding cassettes of two such signalling systems can be linked to produce a symmetric interface for bidirectional communication that can be used to visualise molecular logic. Intracellular feedback between these two cassettes would then create a framework for self-organised patterning of higher complexity. Adapting the experiments of Basu et al. (Basu et al., 2005) using cell motility, rather than a differential response to AHL concentrations as a way to define zones of response, we noted how the interaction of sender and receiver cell populations on a swimming plate could lead to complex pattern formation. Equipping highly motile strains such as E. coli MC1000 with AHL-mediated auto-inducing systems based on Vibrio fischeri luxI/luxR and Pseudomonas aeruginosa lasI/lasR cassettes would allow the amplification of a response to an AHL signal and its propagation. We designed and synthesised codon-optimised auto-inducing luxI/R and lasI/R cassettes as optimal gene expression is crucial for the generation of robust patterns. We still have to complete and test the entire genetic circuitry, although by modelling the system we were able to demonstrate its feasibility. © 2007 The Institution of Engineering and Technology.

Efficient topological localization using orientation adjacency coherence histograms

This paper describes an efficient vision-based global topological localization approach that uses a coarse-to-fine strategy. Orientation Adjacency Coherence Histogram (OACH), a novel image feature, is proposed to improve the coarse localization. The coarse localization results are taken as inputs for the fine localization which is carried out by matching Harris-Laplace interest points characterized by the SIFT descriptor. Computation of OACHs and interest points is efficient due to the fact that these features are computed in an integrated process. We have implemented and tested the localization system in real environments. The experimental results demonstrate that our approach is efficient and reliable in both indoor and outdoor environments. © 2006 IEEE.

Pattern formation and spatial solitons in bistable liquid-crystal microcavities

We report on spatial pattern formation, and appearances of 'optical bullet holes' in single-mode microcavities that are filled with liquid-crystals, when pumped above the cavity resonance frequency. These phenomena only occur beyond the bistability threshold. ©2002 Optical Society of America.