The use of phase in complex spectrum subtraction for robust speech recognition

In this paper we propose a new method for utilising phase information by complementing it with traditional magnitude-only spectral subtraction speech enhancement through Complex Spectrum Subtraction (CSS). The proposed approach has the following advantages over traditional magnitude-only spectral subtraction: (a) it introduces complementary information to the enhancement algorithm; (b) it reduces the total number of algorithmic parameters, and; (c) is designed for improving clean speech magnitude spectra and is therefore suitable for both automatic speech recognition (ASR) and speech perception applications. Oracle-based ASR experiments verify this approach, showing an average of 20% relative word accuracy improvements when accurate estimates of the phase spectrum are available. Based on sinusoidal analysis and assuming stationarity between observations (which is shown to be better approximated as the frame rate is increased), this paper also proposes a novel method for acquiring the phase information called Phase Estimation via Delay Projection (PEDEP). Further oracle ASR experiments validate the potential for the proposed PEDEP technique in ideal conditions. Realistic implementation of CSS with PEDEP shows performance comparable to state of the art spectral subtraction techniques in a range of 15-20 dB signal-to-noise ratio environments. These results clearly demonstrate the potential for using phase spectra in spectral subtractive enhancement applications, and at the same time highlight the need for deriving more accurate phase estimates in a wider range of noise conditions.

Decoupled image-based visual servoing for cameras obeying the unified projection model

This paper proposes a generic decoupled imagebased control scheme for cameras obeying the unified projection model. The scheme is based on the spherical projection model. Invariants to rotational motion are computed from this projection and used to control the translational degrees of freedom. Importantly we form invariants which decrease the sensitivity of the interaction matrix to object depth variation. Finally, the proposed results are validated with experiments using a classical perspective camera as well as a fisheye camera mounted on a 6-DOF robotic platform.

Empirical comparison of machine learning algorithms for image texture classification with application to vegetation management in power line corridors

This paper reports on the empirical comparison of seven machine learning algorithms in texture classification with application to vegetation management in power line corridors. Aiming at classifying tree species in power line corridors, object-based method is employed. Individual tree crowns are segmented as the basic classification units and three classic texture features are extracted as the input to the classification algorithms. Several widely used performance metrics are used to evaluate the classification algorithms. The experimental results demonstrate that the classification performance depends on the performance matrix, the characteristics of datasets and the feature used.

"Re-imagining animation : the changing face of the moving image by Paul Wells and Johnny Hardstaff" (Book Review)

Advances in digital technology have caused a radical shift in moving image culture. This has occurred in both modes of production and sites of exhibition, resulting in a blurring of boundaries that previously defined a range of creative disciplines. Re-Imagining Animation: The Changing Face of the Moving Image, by Paul Wells and Johnny Hardstaff, argues that as a result of these blurred disciplinary boundaries, the term “animation” has become a “catch all” for describing any form of manipulated moving image practice. Understanding animation predicates the need to (re)define the medium within contemporary moving image culture. Via a series of case studies, the book engages with a range of moving image works, interrogating “how the many and varied approaches to making film, graphics, visual artefacts, multimedia and other intimations of motion pictures can now be delineated and understood” (p. 7). The structure and clarity of content make this book ideally suited to any serious study of contemporary animation which accepts animation as a truly interdisciplinary medium.

Attraction and image for the Australian rail industry

Despite the global financial downturn, the Australian rail industry is in a period of expansion. Reports indicate that the industry is not attracting sufficient entry level and mid-career engineers and skilled technicians from within the Australian labour market and is facing widespread retirements from an ageing workforce. This paper reports on a completed qualitative study that explores the perceptions of engineering students, their lecturers, careers advisors and recruitment consultants regarding rail as a brand and of careers in the rail industry. Findings are presented about career knowledge, job characteristic preferences, branding and image and indicate that rail as a brand has a dated image, that young people and their influencers have little knowledge of rail careers and that rail could better focus its image and recruitment strategies. Conclusions include suggestions for more effective attraction and image strategies for the industry and for further research.

Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

Contemporary take on deconstructed Medea : a review

THEATRE: The New Dead: Medea Material. By Heiner Muller. Stella Electrika in association with La Boite Theatre Company, Brisbane, November 19. THERE has been a lot of intensity in independent theatre in Brisbane during the past year, as companies, production houses and producers have begun building new programs and platforms to support an expansion of pathways within the local theatre ecology. Audiences have been exposed to works signalling the diversity of what Brisbane theatre makers want to see on stage, from productions of new local and international pieces to new devised works, and the results of residencies and development programs. La Boite Theatre Company closes its inaugural indie season with a work that places it at the contemporary, experimental end of the spectrum. The New Dead: Medea Material is emerging director Kat Henry's interpretation of Heiner Muller's 1981 text Despoiled Shore Medea Material Landscape with Argonauts. Start of sidebar. Skip to end of sidebar. End of sidebar. Return to start of sidebar. Muller is known for his radical adaptations of historical dramas, from the Greeks to Shakespeare, and for deconstructed texts in which the characters - in this case, Medea - violently reject the familial, cultural and political roles society has laid out for them. Muller's combination of deconstructed characters, disconnected poetic language and constant references to aspects of popular culture and the Cold War politics he sought to abjure make his texts challenging to realise. The poetry entices but the density, together with the increasing distance of the Cold War politics in the texts, leaves contemporary directors with clear decisions to make about how to adapt these open texts. In The New Dead: Medea Material, Henry works with some interesting imagery and conceptual territory. Lucinda Shaw as Medea, Guy Webster as Jason and Kimie Tsukakoshi as King Creon's daughter Glauce, the woman for whom Jason forsakes his wife Medea, each reference different aspects of contemporary culture. Medea is a bitter, drunken, satin-gowned diva with bite; Jason - first seen lounging in front of the television with a beer in an image reminiscent of Sarah Kane's in-yer-face characterisation of Hippolytus in Phaedra's Love - has something of the rock star about him; and Glauce is a roller-skating, karaoke-singing, pole-dancing young temptress. The production is given a contemporary tone, dominated by Medea's twisted love and loss, rather than by any commentary on her circumstances. Its strength is the aesthetic Henry creates, supported by live electro-pop music, a band stage that stands as a metaphor for Jason's sea voyage, and multimedia that inserts images of the story unfolding beyond these characters' speeches as sorts of subconscious flashes. While Tsukakoshi is engaging throughout, there are moments when Shaw and Webster's performances - particularly in the songs - are diminished by a lack of clarity. The result is a piece that, while slightly lacking in its realisation at times, undoubtedly flags Henry's facility as an emerging director and what she wants to bring to the Brisbane theatre scene.

The delta-phase spectrum with application to voice activity detection and speaker recognition

For several reasons, the Fourier phase domain is less favored than the magnitude domain in signal processing and modeling of speech. To correctly analyze the phase, several factors must be considered and compensated, including the effect of the step size, windowing function and other processing parameters. Building on a review of these factors, this paper investigates a spectral representation based on the Instantaneous Frequency Deviation, but in which the step size between processing frames is used in calculating phase changes, rather than the traditional single sample interval. Reflecting these longer intervals, the term delta-phase spectrum is used to distinguish this from instantaneous derivatives. Experiments show that mel-frequency cepstral coefficients features derived from the delta-phase spectrum (termed Mel-Frequency delta-phase features) can produce broadly similar performance to equivalent magnitude domain features for both voice activity detection and speaker recognition tasks. Further, it is shown that the fusion of the magnitude and phase representations yields performance benefits over either in isolation.

A Taxonomy of image matching techniques for stereo vision

Stereo vision is a method of depth perception, in which depth information is inferred from two (or more) images of a scene, taken from different perspectives. Applications of stereo vision include aerial photogrammetry, autonomous vehicle guidance, robotics, industrial automation and stereomicroscopy. A key issue in stereo vision is that of image matching, or identifying corresponding points in a stereo pair. The difference in the positions of corresponding points in image coordinates is termed the parallax or disparity. When the orientation of the two cameras is known, corresponding points may be projected back to find the location of the original object point in world coordinates. Matching techniques are typically categorised according to the nature of the matching primitives they use and the matching strategy they employ. This report provides a detailed taxonomy of image matching techniques, including area based, transform based, feature based, phase based, hybrid, relaxation based, dynamic programming and object space methods. A number of area based matching metrics as well as the rank and census transforms were implemented, in order to investigate their suitability for a real-time stereo sensor for mining automation applications. The requirements of this sensor were speed, robustness, and the ability to produce a dense depth map. The Sum of Absolute Differences matching metric was the least computationally expensive; however, this metric was the most sensitive to radiometric distortion. Metrics such as the Zero Mean Sum of Absolute Differences and Normalised Cross Correlation were the most robust to this type of distortion but introduced additional computational complexity. The rank and census transforms were found to be robust to radiometric distortion, in addition to having low computational complexity. They are therefore prime candidates for a matching algorithm for a stereo sensor for real-time mining applications. A number of issues came to light during this investigation which may merit further work. These include devising a means to evaluate and compare disparity results of different matching algorithms, and finding a method of assigning a level of confidence to a match. Another issue of interest is the possibility of statistically combining the results of different matching algorithms, in order to improve robustness.

Adaptive modelling of sustainable architecture design in entropy evolutionary

This paper argues a model of adaptive design for sustainable architecture within a framework of entropy evolution. The spectrum of sustainable architecture consists of efficient use of energy and material resource in the life-cycle of buildings, active involvement of the occupants into micro-climate control within the building, and the natural environment as the physical context. The interactions amongst all the parameters compose a complex system of sustainable architecture design, of which the conventional linear and fragmented design technologies are insufficient to indicate holistic and ongoing environmental performance. The latest interpretation of the Second Law of Thermodynamics states a microscopic formulation of an entropy evolution of complex open systems. It provides a design framework for an adaptive system evolves for the optimization in open systems, this adaptive system evolves for the optimization of building environmental performance. The paper concludes that adaptive modelling in entropy evolution is a design alternative for sustainable architecture.

Applying ISOMAP to the learning of hyperspectral image

In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive. We propose the use of Isomap, a non-linear manifold learning technique combined with Expectation Maximisation in graphical probabilistic models for learning and classification. Isomap is used to find the underlying manifold of the training data. This low dimensional representation of the hyperspectral data facilitates the learning of a Gaussian Mixture Model representation, whose joint probability distributions can be calculated offline. The learnt model is then applied to the hyperspectral image at runtime and data classification can be performed.