Unifying background models over complex audio using entropy

In this paper we extend an existing audio background modelling technique, leading to a more robust application to complex audio environments. The determination of background audio is used as an initial stage in the analysis of audio for surveillance and monitoring applications. Knowledge of the background serves to highlight unusual or infrequent sounds. An existing modelling approach uses an online, adaptive Gaussian Mixture model technique that uses multiple distributions to model variations in the background. The method used to determine the background distributions of the GMM leads to a failure mode of the existing technique when applied to complex audio. We propose a method incorporating further information, the proximity of distributions determined using entropy, to determine a more complete background model. The method was successful in more robustly modelling the background for complex audio scenes.

Narrative structure detection through audio pace

We use the concept of film pace, expressed through the audio, to analyse the broad level narrative structure of film. The narrative structure is divided into visual narration, action sections, and audio narration, plot development sections. We hypothesise, that changes in the narrative structure signal a change in audio content, which is reflected by a change in audio pace. We test this hypothesis using a number of audio feature functions, that reflect the audio pace, to detect changes in narrative structure for 8 films of varying genres. The properties of the energy were then used to determine the. audio pace feature corresponding to the narrative, structure for each film analysed. The method was successful in determining the narrative structure for 1 of the films, achieving an overall precision of 76.4% and recall of 80.3%, We map the properties of the speech and energy of film audio to the higher level semantic concept of audio pace. The audio pace was in turn applied to a higher level semantic analysis of the structure of film.

Persistent audio modelling for background determination

This paper is concerned with modelling background audio online to detect foreground sounds in complex audio environments for surveillance and smart home applications. We examine and expand upon previous work in the audio and video domains, and propose a new implementation of an audio background modelling algorithm, addressing the complexities of audio data. A number of audio features characterising different aspects of the audio content were analysed to determine the factors relevant to the determination of the background audio. We test the algorithms on three audio data sets of varying complexity. The new approach was successful in modelling the background audio for the test data.

Situated event bootstrapping and capture guidance for automated home movie authoring

This paper describes a novel interactive media authoring framework, MediaTE, that enables amateurs to create videos of higher narrative or aesthetic quality with a completely mobile lifecycle. A novel event bootstrapping dialog is used to derive shot suggestions that yield both targetted footage and annotation enabling an automatic Computational Media Aesthetics-aware editing phase, the manual performance of which is typically a barrier to the amateur. This facilitates a move away from requiring a prior-conception of the events or locale being filmed, in the form of a template, to at-capture bootstrapping of this information. Metadata gathered as part of the critical path of media creation also has implications for the longevity and reuse of captured media assets. Results of an evaluation performed on both the usability and delivered media aspects of the system are discussed, which highlight the tenability of the proposed framework and the quality of the produced media.

Invasive species can't cover their tracks : using microsatellites to assist management of starling (Sturnus vulgaris) populations in Western Australia

Invasive species are known to cause environmental and economic damage, requiring management by control agencies worldwide. These species often become well established in new environments long before their detection, resulting in a lack of knowledge regarding their history and dynamics. When new invasions are discovered, information regarding the source and pathway of the invasion, and the degree of connectivity with other populations can greatly benefit management strategies. Here we use invasive common starling (Sturnus vulgaris) populations from Australia to demonstrate that genetic techniques can provide this information to aid management, even when applied to highly vagile species over continental scales. Analysis of data from 11 microsatellites in 662 individuals sampled at 17 localities across their introduced range in Australia revealed four populations. One population consisted of all sampling sites from the expansion front in Western Australia, where control efforts are focused. Despite evidence of genetic exchange over both contemporary and historical timescales, gene flow is low between this population and all three more easterly populations. This suggests that localized control of starlings on the expansion front may be an achievable goal and the long-standing practice of targeting select proximal eastern source populations may be ineffective on its own. However, even with low levels of gene flow, successful control of starlings on the expansion front will require vigilance, and genetic monitoring of this population can provide essential information to managers. The techniques used here are broadly applicable to invasive populations worldwide.

Robust patchwork-based embedding and decoding scheme for digital audio watermarking

This paper presents a novel patchwork-based embedding and decoding scheme for digital audio watermarking. At the embedding stage, an audio segment is divided into two subsegments and the discrete cosine transform (DCT) coefficients of the subsegments are computed. The DCT coefficients related to a specified frequency region are then partitioned into a number of frame pairs. The DCT frame pairs suitable for watermark embedding are chosen by a selection criterion and watermarks are embedded into the selected DCT frame pairs by modifying their coefficients, controlled by a secret key. The modifications are conducted in such a way that the selection criterion used at the embedding stage can be applied at the decoding stage to identify the watermarked DCT frame pairs. At the decoding stage, the secret key is utilized to extract watermarks from the watermarked DCT frame pairs. Compared with existing patchwork watermarking methods, the proposed scheme does not require information of which frame pairs of the watermarked audio signal enclose watermarks and is more robust to conventional attacks.

Novel watermarking methods for copyright protection of audio signals

This research presented improved watermarking methods for mono and stereo audio signals. To enhance the performance, novel methods are developed using echo hiding techniques and patchwork-based algorithms. The superior performances of the proposed methods are demonstrated by theoretical analysis and simulation examples, in comparison with the existing methods.

ipreps on ipads : exploring the visual/audio nexus of techno-literacy learners in an Australian classroom

This presentation reports on findings from a qualitative study on the use of iPads to support the literacy learning of a group of children who had just commenced their formal schooling in a regional Australian preparatory classroom. Specifically it looks at the affordances the iPad offered to enhance the oral-aural-visual communication of children not yet fluent in print based literacies. The children were interviewed about their techno-literacy learning and observed as they engaged with applications (apps). The researchers were able to video them as they demonstrated high levels of interest, energised learning and a range of independently acquired techno- literacy skills.
There is as yet little research on the use of portable personal computing devices such as the iPad in early years’ classrooms. The children in this study are shown as capable and articulate regarding their iPad use. Beyond the traditionally conceived struggle with passive print decoding when using iPads they become active creators of sophisticated multimodal artefacts that they consider worthy of acclaim, “I’m really proud of myself.” Findings from this study suggest the visual/listening nexus of popular apps potentially challenges print based literacy education approaches and existing paradigms of research and teaching/learning practice in Australian early years’ literacy education.

Enhancing audio-haptic enabled novel dental training platform performance

Existing haptic and non-haptic dental simulators do not eliminate the problem of hand instability while using the haptic devices for training purpose. This paper reports an audio-haptic dental training platform, which uses a Hand Stability System to reduce the effect of nervousness and hand instability for trainee dental students. Maintaining the ease of implementation, application customizability and the cost factor, the proposed platform increases the training efficiency by enhancing the immersive haptic experience with hand stability. This haptic platform includes multiple angle viewing techniques, audio feedback and session recording for after action review. Trials using this preliminary platform reduced the effect of human nervousness and hand instability due to the customized design.

Patchwork-based stereo audio watermarking against de-synchronization attack

Audio watermarking schemes using patchworkbased algorithm have good robustness against majority of the watermarking attacks. However, these watermarking schemes are vulnerable to de-synchronization attack. This paper proposes a patchwork-based watermarking scheme for stereo audio signals to address this problem. To improve the robustness, the proposed method exploits the similarities of both channels in the stereo audio signals. Given a stereo audio signal, we first compute the discrete cosine transform (DCT) of both channels, which gives two sets of DCT coefficients. Then DCT segments are formed form DCT coefficients belong to a certain frequency range. The DCT segment formation is determined by a pseudonoise (PN) sequence which acts as a secret key. Then watermark bits are embedded into DCT segments by modifying the DCT coefficients. In the decoding process the secret key is used to extract the watermark bits embedded in the DCT segments. Simulation results illustrate the effectiveness of the proposed method against de-synchronization attack, compared to latest patchwork-based audio watermarking scheme. Besides, the proposed algorithm also gives better robustness against other conventional attacks.

Human performance measures for interactive haptic-audio-visual interfaces

Virtual reality and simulation are becoming increasingly important in modern society and it is essential to improve our understanding of system usability and efficacy from the users’ perspective. This paper introduces a novel evaluation method designed to assess human user capability when undertaking technical and procedural training using virtual training systems. The evaluation method falls under the user-centred design and evaluation paradigm and draws on theories of cognitive, skillbased and affective learning outcomes. The method focuses on user interaction with haptic-audio-visual interfaces and the complexities related to variability in users’ performance, and the adoption and acceptance of the technologies. A large scale user study focusing on object assembly training tasks involving selecting, rotating, releasing, inserting and manipulating 3D objects was performed. The study demonstrated the advantages of the method in obtaining valuable multimodal information for accurate and comprehensive evaluation of virtual training system efficacy. The study investigated how well users learn, perform, adapt to and perceive the virtual training. The results of the study revealed valuable aspects of the design and evaluation of virtual training systems contributing to an improved understanding of more usable virtual training systems.

Analysis of a patchwork-based audio watermarking scheme

Recently, a patchwork-based audio watermarking scheme has been proposed in [1], which embeds watermarks by modifying the means of absolute-valued discrete cosine transform (DCT) coefficients corresponding to suitable fragments. This audio watermarking scheme is more robust to common attacks than the existing counterparts. In this paper, we presents a detailed analysis of this audio watermarking scheme. We first derive a probability density function (pdf) of a random variable corresponding to the mean of an absolute-valued DCT fragment. Then, based on the obtained pdf, we show how watermarking parameters affect the performance of the concerned audio watermarking scheme. The analysis result provides a guideline for the selection of watermarking parameters. The effectiveness of our analysis is verified by simulations using a large number of real-world audio segments.