👾
I’m Yiannis Tsiamas, an AI Research Scientist and Ph.D. candidate at UPC Barcelona, working on multilinguality, multimodality, text/speech translation, and representation learning. I have authored papers at top-tier conferences like ACL, EMNLP, and ICASSP, and I’ve had the privilege of contributing to cutting-edge research during internships at Meta, Apple, and Dolby.
I am passionate about languages and my goal is to make AI systems trully multilingual, and accessible to everyone.
†Note: I publish under ‘Ioannis Tsiamas’, but use Yiannis as prefered name, which is the casual version Ioannis.
Internship at the Omnilingual team of Meta FAIR.
(Aug 2024 - Present)
Internship at the Machine Translation team of Apple AI/ML.
(Apr 2024 - Jul 2024)
Internship on Audio-Visual Representations at Dolby AI.
(Nov 2023 - Feb 2024)
PhD in Artificial Intelligence at UPC Barcelona.
(Mar 2021 - Present)
MSc in Artificial Intelligence at the University of Amsterdam.
(Graduated Aug 2020)
MSc in Quantitative Finance at VU University Amsterdam.
(Graduated Oct 2018)
We propose a character-based translation model to improve adaptability to new languages and modalities, particularly for low-resource scenarios. Our method achieves …
We introduce Sequential Contrastive Audio-Visual Learning (SCAV), a novel method that contrasts non-aggregated sequential representations to learn fine-grained audio-visual …
We investigate whether speech-to-text translation systems utilize prosody by introducing a new benchmark, ContraProSt. Our findings show that while models represent prosody …
We introduce ZeroSwot, a zero-shot speech translation method that aligns a speech encoder with a multilingual MT model using only ASR data, achieving state-of-the-art results …