A natural evolution of applications that analyze speech is to improve their robustness to multi-speaker environments. Humans use selective auditory attention and can easily switch focus from one source to another even when listening to a single channel recording with overlapped speech. The same brain feature allows us to detect the number of simultaneously active sources. In order to quantify human level performance for this task we have designed a perception study that evaluates participants' ability to accurately count multiple speakers in a single channel audio file. We also analyzed the influence of listening time and of hearing familiar voices. The study was carried in 3 sessions, with the help of 31, 38 and 80 volunteers and significantly extends the findings in existing literature. Using the conclusions from the perception analysis, several convolutional neural networks were trained to estimate the number of competing speakers on speech timeframes ranging from 25 milliseconds to 1 second. The same models were instructed to tag overlapped speech and we observed F-Score values up to 0.91. For both tasks, the proposed methods lead to lower error than existing approaches and require smaller timeframes. Compared with human listeners, the neural networks can count speakers more accurately by analyzing a considerably shorter recording.

This article introduces a novel approach for building a robust Automatic Gesture Recognition system based on Surface Electromyographic (sEMG) signals, acquired at the forearm level. Our main contribution is to propose new constrained learning strategies that ensure robustness against adversarial perturbations by controlling the Lipschitz constant of the classifier. We focus on nonnegative neural networks for which accurate Lipschitz bounds can be derived, and we propose different spectral norm constraints offering robustness guarantees from a theoretical viewpoint. Experimental results on four publicly available datasets highlight that a good tradeoff in terms of accuracy and performance is achieved. We then demonstrate the robustness of our models, compared with standard trained classifiers in four scenarios, considering both white-box and black-box attacks.

Studies have shown that there are different types of cries depending on the newborns' need such as hunger, tiredness, discomfort and so on. Neonatologist or pediatricians can distinguish between different types of cries and can find a pattern in each type of cry. Unfortunately, this is a real problem for the parents who want to act as fast as possible to comfort the newborn. In this paper, we propose a fully automatic system that attempts to discriminate between different types of cries. The baby cry classification system is based on Gaussian Mixture Models and i-vectors. The evaluation is performed on an audio database comprising six types of cries (colic, eructation, discomfort, hunger, pain, tiredness) from 127 babies. The experiments show promising results despite the difficulty of the task.

There is a consistent dependence between integrated circuits (ICs) performance parameters and manufacturing process variations and capturing it at an early development phase represents a major ongoing topic in the semiconductor industry. Typically, this is addressed by the means of Monte Carlo (MC) simulations, where the device model parameters are randomly instantiated according to the technology variations based on a predefined nominal process. Thus, the resulted simulation data can only capture the effect of these variations. This offers little or no insight on the performance’s sensitivities to specific process variations or on the effect of altered statistical technology properties, as it may be the case of process drift or fab-to-fab migration. This article proposes a methodology for modeling the dependency of the device performances (i.e., electrical parameters—EPs) with the influential technology parameters (i.e., process control monitor parameters—PCMs), at an early stage (preSilicon). Using a set of standard MC co-simulations of PCM structures and the circuit schematics (to maintain consistent process variation), it employs a feature selection step to choose the influential PCMs and it trains a machine learning regression algorithm. Both are wrapped up in a Bayesian optimization (BO) framework to find the optimal feature set and the regression hyperparameters. The obtained regression model can explain the functional dependency of the EP on the influential PCMs. Thus, it directly enables sensitivity analysis (SA) to process variation and parametric yield prediction of the IC, as it will be illustrated for the case of an experimental Infineon Technologies product.

Pollen allergies are a cause of much suffering for an increasing number of individuals. Current pollen monitoring techniques are lacking due to their reliance on manual counting and classification of pollen by human technicians. In this study, we present a neural network architecture capable of distinguishing pollen species using data from an automated particle measurement device. This work presents an improvement over the current state of the art in the task of automated pollen classification, using fluorescence spectrum data of aerosol particles. We obtained a relative reduction in the error rate of over 48%, from 27% to 14%, for one of the datasets, with similar improvements for the other analyzed datasets. We also use a novel approach for doing hyperparameter tuning for multiple input networks.

Technological evolution in the remote sensing domain has allowed the acquisition of large archives of satellite image time series (SITS) for Earth Observation. In this context, the need to interpret Earth Observation image time series is continuously increasing and the extraction of information from these archives has become difficult without adequate tools. In this paper, we propose a fast and effective two-step technique for the retrieval of spatio-temporal patterns that are similar to a given query. The method is based on a query-by-example procedure whose inputs are evolution patterns provided by the end-user and outputs are other similar spatio-temporal patterns. The comparison between the temporal sequences and the queries is performed using the Dynamic Time Warping alignment method, whereas the separation between similar and non-similar patterns is determined via Expectation-Maximization. The experiments, which are assessed on both short and long SITS, prove the effectiveness of the proposed SITS retrieval method for different application scenarios. For the short SITS, we considered two application scenarios, namely the construction of two accumulation lakes and flooding caused by heavy rain. For the long SITS, we used a database formed of 88 Landsat images, and we showed that the proposed method is able to retrieve similar patterns of land cover and land use.