Search

Your search keyword '"Beritelli, F"' showing total 157 results
Start Over Author "Beritelli, F"
157 results on '"Beritelli, F"'

4. A new design methodology for window‐based FIR filters.

Author

Avanzato, R., Beritelli, F., Capizzi, G., and Sciuto, G. Lo

Subjects
*FINITE impulse response filters, *GAUSSIAN function, *GABOR filters, *EPISTOLARY fiction, *SIGNAL processing
Abstract

This letter describes a novel window‐based approach to FIR filter design. The window is constructed on the use of equispaced Gaussian basis functions. Unlike other known window‐based methods that do not allow for a satisfactory degree of control over band edges, the proposed method affords very good solution for controlling critical frequencies. In addition, the proposed window method is easier to implement than Kaiser's and affords a better passband flatness than any known design approach. It also yields stopband attenuations and control of critical frequencies which turn out to be very close to those obtainable with Parks–McClellan's method. So the proposed GBR window approach appears to be a significant step forward. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

12. Speech Emotion Recognition Using MFCCs Extracted from a Mobile Terminal based on ETSI Front End

Author

Beritelli, F, Casale, S, Ettorre, D, Russo, A, and Serrano, Salvatore

Subjects
business.industry, Computer science, Speech recognition, Interface (computing), media_common.quotation_subject, Feature extraction, Anger, computer.software_genre, Disgust, Front and back ends, Sadness, Terminal (electronics), Artificial intelligence, business, computer, Natural language processing, media_common, Spoken language
Abstract

The importance of automatically recognizing emotions from human speech has grown with the increasing role of spoken language interface in man-machine applications. The paper presents a system for the recognition of emotional states based on parameters extracted at the front end of a mobile terminal according to the ETSI ES 202 050 standard. Starting from a vector of various features derived from energy and MFCCs, an approach based on genetic algorithms is used to determine a subset of features that will allow robust speech classification of 7 emotional states: anger, joy, sadness, fear, disgust, boredom and neutral

Published
2006

Catalog

Books, media, physical & digital resources
See catalog results