Improving Whispered Speech Recognition Performance Using Pseudo-Whispered Based Data Augmentation

Whispering is a distinct form of speech known for its soft, breathy, and hushed characteristics, often used for private communication. The acoustic characteristics of whispered speech differ substantially from normally phonated speech and the scarcity of adequate training data leads to low automatic speech recognition (ASR) performance. To...

Peculiarities and Experience of W-Band Cloud Radar Calibration

This paper is devoted to discussing peculiarities of W-band cloud radar calibration. After a brief overview of meteorological radar calibration methods for quantitative information retrieval, we focus on problems and their possible solutions with respect to mm-wave radar calibration. The experimental part of the research is based on multi...

Retrieving Information about Remote Objects from Received Signals

This paper considers generalized coherent-polarimetric method of retrieving information about remote objects using electromagnetic waves. Both active and passive electronic systems as well as different objects under observation, operating frequency bands, and physical meaning (interpretation) of the frequency as spectral argument can be used....

Territorial Machines and Integrated Circuits

This research seeks to explicate the transformative power of signal processing in the production of space-time through a transdisciplinary approach across architecture, sound studies, and sonic practice. It combines theory and<br/>practice and consists of two parts, respectively. Part one comprises a transversal genealogy of signal processing,...

Human activity classification with radar signal processing and machine learning

As the number of older adults increases worldwide, new paradigms for indoor activity monitoring are required to keep people living at home independently longer. Radar-based human activity recognition has been identified as a sensing modality of choice because it is privacy-preserving and does not require end-users compliance or manipulation. In...

DeepSHM: A deep learning approach for structural health monitoring based on guided Lamb wave technique

In our previous work, we demonstrated how to use inductive bias to infuse a convolutional neural network (CNN) with domain knowledge from fatigue analysis for aircraft visual NDE. We extend this concept to SHM and therefore in this paper, we present a novel framework called DeepSHM which involves data augmentation of captured sensor signals...

Advanced signal processing techniques for fibre-optic structural health monitoring

Fibre optic sensors can measure a range of physics and chemical parameters. Some of the more common fibre optic sensors are the fibre Bragg grating (FBG), the long period grating (LPG), the Fabry-Pérot Interferometer (FPI) and various distributed fibre optic sensors based on optical time-domain reflectometry (OTDR) and optical frequency domain...