Emanuele Brenna
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Emanuele Brenna has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Franco Di Paolo
University of Rome Tor Vergata
1 shared publication - Giovanni Costantini
Department of Electronic Engineering, University of Rome Tor Vergata, 00133 Rome, Italy
1 shared publication - Lorenzo Valletti
Department of Electronic Engineering, University of Rome Tor Vergata Rome, Italy
1 shared publication - Stefano Fantauzzi
Department of Electronic Engineering, University of Rome Tor Vergata Rome, Italy
1 shared publication - Valerio Cesarini
Department of Electronic Engineering, University of Rome Tor Vergata, 00133 Rome, Italy
1 shared publication
Latest Publications
- Open Access
- 1 June 2023
- Published by FapUNIFESP (SciELO) in Journal of Microwaves, Optoelectronics and Electromagnetic Applications
- Vol. 22 (2) , 280-289
A New Theoretical Approach of Studying Resonances in Single Finline Transitions
In this article an innovative method of studying and removing the resonances, inherently exhibit by some waveguide to microstrip transitions, is presented. By modeling an equivalent circuit, this new approach allows to obtain the constructive parameters of a finline to microstrip transition, only using the values of the resistance and capacitance components of the equivalent circuit. This procedure will allow small microwave design Companies to realize these transitions only implementing circuit analysis software, and not having to afford electromagnetic analysis software, which are very expensive and time-consuming. A full 3D electromagnetic analysis confirms that the simulation results are in excellent agreement with the results obtained by the new equations discussed in this work.
- 1 June 2023
- Published by FapUNIFESP (SciELO) in Journal of Microwaves, Optoelectronics and Electromagnetic Applications
- Vol. 22 (2) , 280-289
Open AccessA New Theoretical Approach of Studying Resonances in Single Finline Transitions
In this article an innovative method of studying and removing the resonances, inherently exhibit by some waveguide to microstrip transitions, is presented. By modeling an equivalent circuit, this new approach allows to obtain the constructive parameters of a finline to microstrip transition, only using the values of the resistance and capacitance components of the equivalent circuit. This procedure will allow small microwave design Companies to realize these transitions only implementing circuit analysis software, and not having to afford electromagnetic analysis software, which are very expensive and time-consuming. A full 3D electromagnetic analysis confirms that the simulation results are in excellent agreement with the results obtained by the new equations discussed in this work.
- Open Access
High-Level CNN and Machine Learning Methods for Speaker Recognition
Speaker Recognition (SR) is a common task in AI-based sound analysis, involving structurally different methodologies such as Deep Learning or “traditional” Machine Learning (ML). In this paper, we compared and explored the two methodologies on the DEMoS dataset consisting of 8869 audio files of 58 speakers in different emotional states. A custom CNN is compared to several pre-trained nets using image inputs of spectrograms and Cepstral-temporal (MFCC) graphs. AML approach based on acoustic feature extraction, selection and multi-class classification by means of a Naïve Bayes model is also considered. Results show how a custom, less deep CNN trained on grayscale spectrogram images obtain the most accurate results, 90.15% on grayscale spectrograms and 83.17% on colored MFCC. AlexNet provides comparable results, reaching 89.28% on spectrograms and 83.43% on MFCC.The Naïve Bayes classifier provides a 87.09% accuracy and a 0.985 average AUC while being faster to train and more interpretable. Feature selection shows how F0, MFCC and voicing-related features are the most characterizing for this SR task. The high amount of training samples and the emotional content of the DEMoS dataset better reflect a real case scenario for speaker recognition, and account for the generalization power of the models.
Open AccessHigh-Level CNN and Machine Learning Methods for Speaker Recognition
Speaker Recognition (SR) is a common task in AI-based sound analysis, involving structurally different methodologies such as Deep Learning or “traditional” Machine Learning (ML). In this paper, we compared and explored the two methodologies on the DEMoS dataset consisting of 8869 audio files of 58 speakers in different emotional states. A custom CNN is compared to several pre-trained nets using image inputs of spectrograms and Cepstral-temporal (MFCC) graphs. AML approach based on acoustic feature extraction, selection and multi-class classification by means of a Naïve Bayes model is also considered. Results show how a custom, less deep CNN trained on grayscale spectrogram images obtain the most accurate results, 90.15% on grayscale spectrograms and 83.17% on colored MFCC. AlexNet provides comparable results, reaching 89.28% on spectrograms and 83.43% on MFCC.The Naïve Bayes classifier provides a 87.09% accuracy and a 0.985 average AUC while being faster to train and more interpretable. Feature selection shows how F0, MFCC and voicing-related features are the most characterizing for this SR task. The high amount of training samples and the emotional content of the DEMoS dataset better reflect a real case scenario for speaker recognition, and account for the generalization power of the models.