Dottorato in Ingegneria Informatica E Dei Sistemi , 36o ciclo (2020-2023)
Dottorato concluso nel 2024
Tesi:
Speaker Verification and Language Recognition (Abstract)
Tutori:
Sandro Cumani
Presentazione della ricerca:
Presentazione video PosterProfilo
Argomento di ricerca
Speaker verification and multi-modal identity recognition
Interessi di ricerca
Biografia
I come from a small city in the south of Italy but always felt a strong willingness to go and experience the world. Following this desire and given the opportunity, I lived for two years in Vatican City, frequenting middle schools in Rome. I returned to my hometown and decided to attend a scientific high school there. The smartphone revolution and the following cultural changes confirmed to me that a few single minds and the force of their ideas in other people could change the world and society. Computer engineering felt like a natural choice. Politecnico di Torino had the best offer for me, so I attended its courses obtaining both bachelor's and master's degrees in computer engineering. During my thesis work, I met the Ph.D. world, and thanks to the encouragement finally decided to further extend my knowledge in the machine learning and AI field, focusing on speaker verification related problems.
Didattica
Insegnamenti
Corso di laurea magistrale
- Machine learning and pattern recognition. A.A. 2020/21, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
- Machine learning and pattern recognition. A.A. 2021/22, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
- Machine learning and pattern recognition. A.A. 2022/23, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
- Machine learning and pattern recognition. A.A. 2023/24, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
Corso di laurea di 1° livello
- Computer sciences. A.A. 2023/24, INGEGNERIA DELL'AUTOVEICOLO (AUTOMOTIVE ENGINEERING). Collaboratore del corso
Pubblicazioni
Pubblicazioni durante il dottorato Vedi tutte le pubblicazioni su Porto@Iris
- Sarni, Salvatore (2024)
Speaker Verification and Language Recognition. relatore: CUMANI, SANDRO; , 36. XXXVI Ciclo, P.: 132
Doctoral Thesis - Sarni, Salvatore; Cumani, Sandro; Siniscalchi, Sabato Marco; Bottino, Andrea (2023)
Description and analysis of the KPT system for NIST Language Recognition Evaluation 2022. In: 24th INTERSPEECH Conference 2023, Dublin (IRL), 20th – 24th August 2023, pp. 1933-1937
Contributo in Atti di Convegno (Proceeding) - Cumani, S; Sarni, S (2023)
The Distributions of Uncalibrated Speaker Verification Scores: A Generative Model for Domain Mismatch and Trial-Dependent Calibration. In: IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, vol. 31, pp. 2204-2219. ISSN 2329-9290
Contributo su Rivista - Cumani, Sandro; Sarni, Salvatore (2023)
From adaptive score normalization to adaptive data normalization for speaker verification systems. In: INTERSPEECH 2023, Dublin (IE), 20th - 24th August 2023, pp. 5296-5300
Contributo in Atti di Convegno (Proceeding) - Cumani, Sandro; Sarni, Salvatore (2022)
Impostor Score Statistics as Quality Measures for the Calibration of Speaker Verification Systems. In: Odyssey 2022: The Speaker and Language Recognition Workshop, Beijing (CN), 28 June - 1 July 2022, pp. 25-32
Contributo in Atti di Convegno (Proceeding) - Cumani, Sandro; Sarni, Salvatore (2021)
A Generative Model for Duration-Dependent Score Calibration. In: Interspeech 2021, Brno (Repubblica Ceca), 30 August - 3 September 2021, pp. 4598-4602
Contributo in Atti di Convegno (Proceeding)