Missing data imputation estimates the clean speech features for automatic speech recognition in noisy environments. The estimates are usually considered equally reliable while in reality, the estimation accuracy varies from feature to feature. In this work, we propose uncertainty measures to characterise the expected accuracy of a sparse imputation (SI) based missing data method. In experiments...

This paper focuses on an extensive market analysis done under the framework of the Peach coordination action, a project funded by the European Union Future Emerging Technologies unit. The analysis identifies, classifies, reports and further elaborates on which areas presently benefit from Presence technologies. Taxonomy of these markets is also derived in this document, describing how and why P...

Presence has become a key concept in characterizing and evaluating Virtual Environments. Our contribution is to show that current measures of Presence, as a metric of users’ experience of Virtual Environments, are highly problematic: results from the literature cannot be repeated and it lacks a theoretical basis. We synthesize results from three experiments we conducted and in conclusion point ...

This work presents an automatic speech recognition system which uses a missing data approach to compensate for environmental noise. The missing, noise-corrupted components are identified using binaural features or a support vector machine (SVM) classifier. To perform speech recognition using the partially observed data, the missing components are substituted with clean speech estimates calculat...

Spoken language is one of the most intuitive forms of interaction between humans and agents. Unfortunately, agents that interact with people using natural language often experience communication errors and do not correctly understand the user’s intentions. Recent systems have successfully used probabilistic models of speech, language, and user behavior to generate robust dialog performance in t...

In this research, first, kinematic and dynamic equations of a 4-DOF 3-link robotic finger are derived using Denavit-Hartenberg convention and Lagrange’s formulation. To model the muscles, several springs and dampers are placed between the finger links. Then, two advanced controllers, namely adaptive-robust and adaptive-neural, which can control the robotic finger in presence of parametric uncer...

We propose time-frequency domain methods for noise estimation and speech enhancement. A speech presence detection method is used to find connected time-frequency regions of speech presence. These regions are used by a noise estimationmethod and both the speech presence decisions and the noise estimate are used in the speech enhancement method. Different attenuation rules are applied to regions ...

background: speech perception ability depends on auditory and extra-auditory elements. the signal-to-noise ratio (snr) is an extra-auditory element that has an effect on the ability to normally follow speech and maintain a conversation. speech in noise perception difficulty is a common complaint of the elderly. in this study, the importance of snr magnitude as an extra-auditory effect on speech...