The article compares two approaches to the description of ultrasound vocal tract images for application in a "silent speech interface," one based on tongue contour modeling, and a second, global coding approach in which images are projected onto a feature space of Eigentongues. A curvature-based lip profile feature extraction method is also presented. Extracted visual features are input to a neural network which learns the relation between the vocal tract configuration and line spectrum frequencies (LSF) contained in a one-hour speech corpus. An examination of the quality of LSFs derived from the two approaches demonstrates that the Eigemongues approach has a more efficient implementation and provides superior results based on a normalized mean squared error criterion.

A new contour-tracking algorithm is presented for ultrasound tongue image sequences, which can follow the motion of tongue contours over long durations with good robustness. To cope with missing segments caused by noise, or by the tongue midsagittal surface being parallel to the direction of ultrasound wave propagation, active contours with a contour-similarity constraint are introduced, which can be used to provide ‘prior’ shape information. Also, in order to address accumulation of tracking errors over long sequences, we present an automatic re-initialization technique, based on the complex wavelet image similarity index. Experiments on synthetic data and on real 60 frame per second (fps) data from different subjects demonstrate that the proposed method gives good contour tracking for ultrasound image sequences even over durations of minutes, which can be useful in applications such as speech recognition where very long sequences must be analyzed in their entirety.

The feasibility of a silent speech interface using ultrasound (US) imaging and lip profile video is investigated by examining the quality of line spectral frequencies (LSF) derived from the image sequences. It is found that the data do not at present allow reliable identification of silences and fricatives, but that LSF's recovered from vocalized passages are compatible with the synthesis of intelligible speech

A new approach to indoor localization is presented, based upon the use of Received Signal Strength (RSS) fingerprints containing data from very large numbers of cellular base stations--up to the entire GSM band of over 500 channels. Machine learning techniques are employed to extract good quality location information from these high-dimensionality input vectors. Experimental results in a domestic and an office setting are presented, in which data were accumulated over a 1-month period in order to assure time robustness. Room-level classification efficiencies approaching 100% were obtained, using Support Vector Machines in one-versus-one and one-versus-all configurations. Promising results using semi-supervised learning techniques, in which only a fraction of the training data is required to have a room label, are also presented. While indoor RSS localization using WiFi, as well as some rather mediocre results with low-carrier count GSM fingerprints, have been discussed elsewhere, this is to our knowledge the first study to demonstrate that good quality indoor localization information can be obtained, in diverse settings, by applying a machine learning strategy to RSS vectors that contain the entire GSM band.

In the past few years, the ability of wireless network operators to monitor audience using control frames emitted by client devices has been compromised, both by legislation treating client MAC addresses as private information and by the difficulty of distinguishing genuine client frames from those arising from the Internet of Things or from certain enhanced services. Here, a deterministic model, based on characteristics of human activity and on seasonal trends, is used to reveal underlying client statistics in raw MAC-randomized WiFi Probe Request data. The method proposes a candidate conversion factor, X, between probe request counts and the client population, which offers plausible predictions on real-world datasets.

Representation learning is believed to produce high-level representations of underlying dynamics in temporal sequences. A three-dimensional convolutional neural network trained to predict future frames in ultrasound tongue and optical lip images creates features for a continuous hidden Markov model based speech recognition system. Predictive tongue features are found to generate lower word error rates than those obtained from an auto-encoder without future frames, or from discrete cosine transforms. Improvement is apparent for the monophone/triphone Gaussian mixture model and deep neural network acoustic models. When tongue and lip modalities are combined, the advantage of the predictive features is reduced.