- Silvia Alma Piazzolla. degree obtained: Laura Magistrale – LM, Università di Trento (Italy). Dissertation: “Gender bias in commercial MT systems: a comparative evaluation on the MuST-SHE benchmark”, 2022
- Andrea Piergentili , degree obtained: Laurea Magistrale – LM, Lingue e Culture per la Comunicazione e Cooperazione Internazionale, Università dell’Aquila (Italy). Dissertation: “Creation of a multilingual benchmark for the evaluation of gender neutral automatic translation”, 2022
- Francesca Onorato, degree obtained: Laurea in Computer Science, University of Trento (Italy), Dissertation “Segmentation Strategies for End-to-End Simultaneous Speech Translation”, 2021
- Antonio Vespoli, degree obtained: Laurea in Computer Science, University of Trento (Italy), Dissertation: “Data-to-Text: Generating Forecast Bulletins from Raw Data”, 2020
- Andrea Alfieri, degree obtained: Master of Arts – MA, Specialized Translation, U. Bologna-Forlì, 2020
- Nicholas Ruiz, degree obtained: European Master Erasmus Mundus Language & Communication Technologies, Free University of Bozen-Bolzano, 2011.
- Diego Pineda, degree obtained: European Master in Language and Speech, Universitat Politècnica de Catalunya, 2006. Dissertation: “A Punctuation Detector in Speech Recognition”. Now with SOGETI, Barcelona, Spain.
- Florian Hönig, degree obatined: Master in Electronic Engineering, Erlangen-Nuremberg University, 2005. Dissertation: “Modifications of Perceptual Linear Prediction and the Mel-Frequency Cepstrum”. Now PhD student at Erlangen-Nuremberg University, Germany.
- Michele Vescovi, degree obtained: degree in informatics, U. Trento, Mar 2003. Dissertation: “Algoritmi per la segmentazione audio basati sul criterio di informazione bayesiano: analisi, implementazione e sperimentazione”. Now PhD Student at U. of Trento.
- Erwin Leeuwis, degree obtained: degree in informatics, U. Twente, Feb 2003. Dissertation: “A Language Model for an ASR System for Lectures”. Now at Capgemini, Utrecht Area, Netherlands.
- Nicola Bertoldi, degree obtained: Laurea degree in mathematics, U. Trento, 2000. Dissertation: “Analysis and implementation of Statistical Models for POS tagging”. Now staff researcher at FBK-irst.
- Christian Girardi, degree obtained: degree in informatics, U. Trento, 2000. Dissertation: “Sviluppo di un’interfaccia grafica per un sistema di comunicazione vocale multilingua”. Now at FBK-irst.
🇦🇹 I’ll be in Vienna for #ACL2025NLP!
Interested in training a SpeechLLM without a lot of params or data? Come to my poster:
🖼️ Mon, 18:00
Also into Speech Summarization? Join my IWSLT talk in collab with @fbk_mt:
🎤 Fri, 14:00
Happy to chat - come say hi! 😎
Papers in 🧵
Sara Papi, Maike Z\"ufle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues, "MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks,"
Our pick of the week by @mgaido91: "WhisperKit: On-device Real-time ASR with Billion-Scale Transformers" by Atila Orhon, Arda Okan, Berkin Durmus, @zachnagengast, and Eduardo Pacheco (ICML 2025)
#speech #speechtech #whisper #ASR #realtime
A couple of weeks before presenting our large-scale speech model compression task at IWSLT, here there is of the first attempts to bring large-scale models to the devices on the edge: https://arxiv.org/pdf/2507.10860... Hope to see more works along this direction!
Our pick of the week by @FBKZhihangXie: "Adversarial Speech-Text Pre-Training for Speech Translation" by Chenxuan Liu, Liping Chen, Weitai Zhang, Xiaoxi Li, Peiwang Tang, Mingjia Yu, Sreyan Ghosh, and Zhongyi Ye (ICASSP 2025)
#speech #speechprocessing #speechtech #translation
🚀 AdvST: Adversarial training aligns speech and text distributions without parallel data! Combines adversarial learning + hidden-state swapping to fix length mismatch & boost low-resource speech translation. https://ieeexplore.ieee.org/document/10888294