- Marco Turchi, post-doc in machine translation. Now at Zoom Video Communications.
- Nicola Bertoldi, post-doc in machine translation. Now at Translated, Italy.
- Dino Seppi, post-doc in automatic speech recognition. Dino moved to Polderland Language & Speech Technology in Nijmegen (NL), and then to Leuven University, Belgium.
- Gabriele Musillo, post-doc in machine translation, Oct 2009-Aug 2010. Project: EuromatrixPlus. Currently senior researcher for Localot Research, Boston.
- Boxing Chen, post-doc in machine translation, Jan 2005-Mar 2007. Project: TC-STAR. Currently senior researcher at Institute of Infocomm Research, Singapore.
- Deepa Gupta, post-doc in machine translation, Jan 2005-Mar 2007. Project: TC-STAR. Now at IIIT – Indian Institute of Information Technology, Bangalore, India.
- Georg Stemmer, post-doc in automatic speech recognition, Sep 2003-Mar 2005. Post-doc grant from the autonomous Province of Trento. Now with Siemens AG, Munich, Germany.
⭐ For our #PickOfTheWeek, this paper explores an important question for modern speech AI:
🎙️ Which Evaluation for Which Speech Model?
👥 Authors: @Maureendss , @EeshanDhekane
Speech foundation models are evolving rapidly, but evaluation practices are still fragmented.
🏝️ Yesterday at #LREC2026, Palma de Mallorca!
@lina_conti presented "Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation" at the poster session.
📄Paper:
💻Code: https://github.com/lina-conti/voice-bias-coreference
#SpeechTranslation #NLProc
How does the granularity of speech-text pairs impact SpeechLLM performance, and what is the optimal way to interleave tokens? Furthermore, what are the best practices for generating synthetic data to boost training?🧐