no code implementations • 15 May 2013 • Mohammad Pourhomayoun, Peter Dugan, Marian Popescu, Christopher Clark
In this paper, we develop a novel method based on machine-learning and image processing to identify North Atlantic right whale (NARW) up-calls in the presence of high levels of ambient and interfering noise.
no code implementations • 15 May 2013 • Mohammad Pourhomayoun, Peter Dugan, Marian Popescu, Denise Risch, Hal Lewis, Christopher Clark
In this paper, we propose a method to improve sound classification performance by combining signal features, derived from the time-frequency spectrogram, with human perception.
no code implementations • 14 May 2013 • Marian Popescu, Peter J. Dugan, Mohammad Pourhomayoun, Denise Risch, Harold W. Lewis III, Christopher W. Clark
The following work outlines an approach for automatic detection and recognition of periodic pulse train signals using a multi-stage process based on spectrogram edge detection, energy projection and classification.