Search

Your search keyword '"Benedetto, Luigi Di"' showing total 15 results
Start Over Author "Benedetto, Luigi Di"
15 results on '"Benedetto, Luigi Di"'

2. Automatic Audio Feature Extraction for Keyword Spotting

Author

Vitolo, Paola, Liguori, Rosalba, Benedetto, Luigi Di, Rubino, Alfredo, and Licciardo, Gian Domenico

Abstract

The accuracy and computational complexity of keyword spotting (KWS) systems are heavily influenced by the choice of audio features in speech signals. This letter introduces a novel approach for audio feature extraction in KWS by leveraging a convolutional autoencoder, which has not been explored in the existing literature. Strengths of the proposed approach are in the ability to automate the extraction of the audio features, keep its computational complexity low, and allow accuracy values of the overall KWS systems comparable with the state of the art. To evaluate the effectiveness of our proposal, we compared it with the widely-used Mel Frequency Cepstrum (MFC) method in terms of classification metrics in noisy conditions and the number of required operators, using the public Google speech command dataset. Results demonstrate that the proposed audio feature extractor achieves an average classification accuracy on 12 classes ranging from 81.84% to 90.36% when the signal-to-noise ratio spans from 0 to 40 dB, outperforming the MFC up to 5.2%. Furthermore, the required number of operations is one order of magnitude lower than that of the MFC, resulting in a reduction in computational complexity and processing time, which makes it well-suited for integration with KWS systems in resource-constrained edge devices.

Published
2024
Full Text
View/download PDF

15. Optimized design for 4H-SiC power DMOSFETs

Author

Benedetto, Luigi di, Licciardo, Gian D., Erlbacher, Tobias, Bauer, Anton J., Rubino, Alfredo, and Publica

Subjects
design methodology, silicon compound, Power MOSFET, semiconductor device modeling
Abstract

An optimized tradeoff between blocking voltage and specific ON-resistance for 4H-silicon carbide power vertical double-implanted metal-oxide-semiconductor field-effect transistor (DMOSFET) is exclusively obtained as a function of doping concentration in the drift region. Based on a novel analytical model of the electric field in the gate oxide of 4H-SiC DMOSFETs, we propose a closed-form equation of the Junction FET (JFET) region width and the drift thickness as function of doping concentration without using fitting and empirical parameters to obtain the maximum figure of merit. Model results are successfully verified with TCAD numerical simulations, covering a wide range of device performances, and experimental results.

Published
2016

Catalog

Books, media, physical & digital resources
See catalog results