C
Constantine Kotropoulos
Researcher at Aristotle University of Thessaloniki
Publications - 251
Citations - 6212
Constantine Kotropoulos is an academic researcher from Aristotle University of Thessaloniki. The author has contributed to research in topics: Support vector machine & Feature vector. The author has an hindex of 41, co-authored 245 publications receiving 5869 citations.
Papers
More filters
Comparative study of speaker verification techniques based on vector quantization, sphericity models
TL;DR: In this paper, three simple speaker verification techniques based on vector quantization, sphericity models and dynamic time warping are developed and tested using the same experimental protocol, and the efficiency of the combination of the type of acoustic analysis and the verification technique is quantitatively measured through the achieved equal error rate.
Comparativ estud yo fspeake rverificatio ntechniques base do nvecto rquantization ,sphericit ymodel sand dynami ctim ewarping*
TL;DR: In this article, three simple speaker verification techniques based on vector quantization, sphericity mod- els and dynamic time warping, respectively, are developed and tested using the same experimental pro- tocol. The efficiency of the combination of the type of acoustic analysis and the verification technique is quantita- tively measured through the achieved equal error rate.
Proceedings Article
Musical Audio Denoising Assuming Symmetric α-Stable Noise.
TL;DR: Experiments on noisy Greek folk music excerpts demonstrate better denoising under the α-stable noise assumption than the Gaussian white noise one, when processing is performed in segments rather than in full recordings.
Book ChapterDOI
Techniques in Knowledge-Based Signal/Image Processing and Their Application in Geophysical Image Interpretation
Proceedings ArticleDOI
Robust multidimensional scaling employing M-estimators and nuclear norm regularization
TL;DR: To cope with gross errors, two algorithms are proposed, which resort to half-quadratic optimization, employing M-estimators and nuclear norm regularization, and outperform the state-of-the-art MDS ones.