Noise robust voice activity detection using features extracted from the time-domain autocorrelation function

This paper presents a method of voice activity detection (VAD) for high noise scenarios, using a noise robust voiced speech detection feature. The developed method is based on the fusion of two systems. The first system utilises the maximum peak of the normalised time-domain autocorrelation function (MaxPeak). The second zone system uses a novel combination of cross-correlation and zero-crossing rate of the normalised autocorrelation to approximate a measure of signal pitch and periodicity (CrossCorr) that is hypothesised to be noise robust. The score outputs by the two systems are then merged using weighted sum fusion to create the proposed autocorrelation zero-crossing rate (AZR) VAD. Accuracy of AZR was compared to state of the art and standardised VAD methods and was shown to outperform the best performing system with an average relative improvement of 24.8% in half-total error rate (HTER) on the QUT-NOISE-TIMIT database created using real recordings from high-noise environments.

Listening in to others : in between noise and silence

Since the launch of the ‘Clean Delhi, Green Delhi’ campaign in 2003, slums have become a significant social and political issue in India’s capital city. Through this campaign, the state, in collaboration with Delhi’s middle class through the ‘Bhagidari system’ (literally translated as ‘participatory system’), aims to transform Delhi into a ‘world-class city’ that offers a sanitised, aesthetically appealing urban experience to its citizens and Western visitors. In 2007, Delhi won the bid to host the 2010 Commonwealth Games; since then, this agenda has acquired an urgent, almost violent, impetus to transform Delhi into an environmentally friendly, aesthetically appealing and ‘truly international city’. Slums and slum-dwellers, with their ‘filth, dirt, and noise’, have no place in this imagined city. The violence inflicted upon slum-dwellers, including the denial of their judicial rights, is justified on these accounts. In addition, the juridical discourse since 2000 has ‘re-problematised slums as ‘nuisance’. The rising antagonism of the middle-classes against the poor, supported by the state’s ambition to have a ‘world-class city’, has allowed a new rhetoric to situate the slums in the city. These representations articulate slums as homogenised spaces of experience and identity. The ‘illegal’ status of slum-dwellers, as encroachers upon public space, is stretched to involve ‘social, cultural, and moral’ decadence and depravity. This thesis is an ethnographic exploration of everyday life in a prominent slum settlement in Delhi. It sensually examines the social, cultural and political materiality of slums, and the relationship of slums with the middle class. In doing so, it highlights the politics of sensorial ordering of slums as ‘filthy, dirty, and noisy’ by the middle classes to calcify their position as ‘others’ in order to further segregate, exclude and discriminate the slums. The ethnographic experience in the slums, however, highlights a complex sensorial ordering and politics of its own. Not only are the interactions between diverse communities in slums highly restricted and sensually ordained, but the middle class is identified as a sensual ‘other’, and its sensual practices prohibited. This is significant in two ways. First, it highlights the multiplicity of social, cultural experience and engagement in the slums, thereby challenging its homogenised representation. Second, the ethnographic exploration allowed me to frame a distinct sense of self amongst the slums, which is denied in mainstream discourses, and allowed me to identify the slums’ own ’others’, middle class being one of them. This thesis highlights sound – its production, performances and articulations – as an act with social, cultural, and political implications and manifestations. ‘Noise’ can be understood as a political construct to identify ‘others’ – and both slum-dwellers and the middle classes identify different sonic practices as noise to situate the ‘other’ sonically. It is within this context that this thesis frames the position of Listener and Hearer, which corresponds to their social-political positions. These positions can be, and are, resisted and circumvented through sonic practices. For instance, amplification tactics in the Karimnagar slums, which are understood as ‘uncultured, callous activities to just create more noise’ by the slums’ middle-class neighbours, also serve definite purposes in shaping and navigating the space through the slums’ soundscapes, asserting a presence that is otherwise denied. Such tactics allow the residents to define their sonic territories and scope of sonic performances; they are significant in terms of exerting one’s position, territory and identity, and they are very important in subverting hierarchies. The residents of the Karimnagar slums have to negotiate many social, cultural, moral and political prejudices in their everyday lives. Their identity is constantly under scrutiny and threat. However, the sonic cultures and practices in the Karimnagar slums allow their residents to exert a definite sonic presence – which the middle class has to hear. The articulation of noise and silence is an act manifesting, referencing and resisting social, cultural, and political power and hierarchies.

Deterministic diffraction loss modelling for novel broadband communication in rural environments

This paper presents a deterministic modelling approach to predict diffraction loss for an innovative Multi-User-Single-Antenna (MUSA) MIMO technology, proposed for rural Australian environments. In order to calculate diffraction loss, six receivers have been considered around an access point in a selected rural environment. Generated terrain profiles for six receivers are presented in this paper. Simulation results using classical diffraction models and diffraction theory are also presented by accounting the rural Australian terrain data. Results show that in an area of 900 m by 900 m surrounding the receivers, path loss due to diffraction can range between 5 dB and 35 dB. Diffraction loss maps can contribute to determine the optimal location for receivers of MUSA-MIMO systems in rural areas.

Living well with diabetes: a randomized controlled trial of a telephone-delivered intervention for maintenance of weight loss, physical activity and glycaemic control in adults with type 2 diabetes

Background By 2025, it is estimated that approximately 1.8 million Australian adults (approximately 8.4% of the adult population) will have diabetes, with the majority having type 2 diabetes. Weight management via improved physical activity and diet is the cornerstone of type 2 diabetes management. However, the majority of weight loss trials in diabetes have evaluated short-term, intensive clinic-based interventions that, while producing short-term outcomes, have failed to address issues of maintenance and broad population reach. Telephone-delivered interventions have the potential to address these gaps. Methods/Design Using a two-arm randomised controlled design, this study will evaluate an 18-month, telephone-delivered, behavioural weight loss intervention focussing on physical activity, diet and behavioural therapy, versus usual care, with follow-up at 24 months. Three-hundred adult participants, aged 20-75 years, with type 2 diabetes, will be recruited from 10 general practices via electronic medical records search. The Social-Cognitive Theory driven intervention involves a six-month intensive phase (4 weekly calls and 11 fortnightly calls) and a 12-month maintenance phase (one call per month). Primary outcomes, assessed at 6, 18 and 24 months, are: weight loss, physical activity, and glycaemic control (HbA1c), with weight loss and physical activity also measured at 12 months. Incremental cost-effectiveness will also be examined. Study recruitment began in February 2009, with final data collection expected by February 2013. Discussion This is the first study to evaluate the telephone as the primary method of delivering a behavioural weight loss intervention in type 2 diabetes. The evaluation of maintenance outcomes (6 months following the end of intervention), the use of accelerometers to objectively measure physical activity, and the inclusion of a cost-effectiveness analysis will advance the science of broad reach approaches to weight control and health behaviour change, and will build the evidence base needed to advocate for the translation of this work into population health practice.

The effects of weight loss strategies on gastric emptying and appetite control

The gastrointestinal tract plays an important role in the improved appetite control and weight loss in response to bariatric surgery. Other strategies which similarly alter gastrointestinal responses to food intake could contribute to successful weight management. The aim of this review is to discuss the effects of surgical, pharmacological and behavioural weight loss interventions on gastrointestinal targets of appetite control, including gastric emptying. Gastrointestinal peptides are also discussed because of their integrative relationship in appetite control. This review shows that different strategies exert diverse effects and there is no consensus on the optimal strategy for manipulating gastric emptying to improve appetite control. Emerging evidence from surgical procedures (e.g., sleeve gastrectomy and Roux en-Y gastric bypass) suggests a faster emptying rate and earlier delivery of nutrients to the distal small intestine may improve appetite control. Energy restriction slows gastric emptying, while the effect of exercise-induced weight loss on gastric emptying remains to be established. The limited evidence suggests that chronic exercise is associated with faster gastric emptying which we hypothesise will impact on appetite control and energy balance. Understanding how behavioural weight loss interventions (e.g., diet and exercise) alter gastrointestinal targets of appetite control may be important to improve their success in weight management.

Convexity, Classification, and Risk Bounds

Many of the classification algorithms developed in the machine learning literature, including the support vector machine and boosting, can be viewed as minimum contrast methods that minimize a convex surrogate of the 0–1 loss function. The convexity makes these algorithms computationally efficient. The use of a surrogate, however, has statistical consequences that must be balanced against the computational virtues of convexity. To study these issues, we provide a general quantitative relationship between the risk as assessed using the 0–1 loss and the risk as assessed using any nonnegative surrogate loss function. We show that this relationship gives nontrivial upper bounds on excess risk under the weakest possible condition on the loss function—that it satisfies a pointwise form of Fisher consistency for classification. The relationship is based on a simple variational transformation of the loss function that is easy to compute in many applications. We also present a refined version of this result in the case of low noise, and show that in this case, strictly convex loss functions lead to faster rates of convergence of the risk than would be implied by standard uniform convergence arguments. Finally, we present applications of our results to the estimation of convergence rates in function classes that are scaled convex hulls of a finite-dimensional base class, with a variety of commonly used loss functions.

Correction to “The Importance of Convexity in Learning With Squared Loss” [Sep 98 1974-1980]

The paper "the importance of convexity in learning with squared loss" gave a lower bound on the sample complexity of learning with quadratic loss using a nonconvex function class. The proof contains an error. We show that the lower bound is true under a stronger condition that holds for many cases of interest.

Classification with a reject option using a hinge loss

We consider the problem of binary classification where the classifier can, for a particular cost, choose not to classify an observation. Just as in the conventional classification problem, minimization of the sample average of the cost is a difficult optimization problem. As an alternative, we propose the optimization of a certain convex loss function φ, analogous to the hinge loss used in support vector machines (SVMs). Its convexity ensures that the sample average of this surrogate loss can be efficiently minimized. We study its statistical properties. We show that minimizing the expected surrogate loss—the φ-risk—also minimizes the risk. We also study the rate at which the φ-risk approaches its minimum value. We show that fast rates are possible when the conditional probability P(Y=1|X) is unlikely to be close to certain critical values.