Sara Papi

Sara Papi

Post-doc in Speech Translation

Fondazione Bruno Kessler (MT Unit)

🐘 Biography

I am a post-doc in Computer Science, specifically in speech translation, at FBK (Fondazione Bruno Kessler) in the MT Unit. I am interested in speech processing in general and its applications, with a particular focus on simultaneous translation and automatic subtitling, which were the topics of my PhD.

(I love elephants ♥️🐘)

Leave an anonymous feedback here! 😊

Interests
  • Artificial Intelligence
  • Computational Linguistics
  • Speech Processing
  • Simultaneous Translation
Education
  • PhD in Information and Communication Technology

    University of Trento, 2020 - 2024

  • MSc in Computer and Automation Engineering

    University of Siena, 2017 - 2020

  • BSc in Information Engineering

    University of Siena, 2014-2017

🏃 Experience

 
 
 
 
 
Fondazione Bruno Kessler
PostDoc
January 2024 – Present Trento, Italy
PostDoc in Speech Translation, working on the Meetween European Project.
 
 
 
 
 
Microsoft
Research Intern
May 2023 – August 2023 Redmond, WA (USA)
Internship in Streaming Speech Recognition and Translation, working with Jinyu Li et al.
 
 
 
 
 
Fondazione Bruno Kessler
Resarch Intern
July 2020 – October 2020 Trento, Italy
Internship in data-to-text generation for weather forecasting.
 
 
 
 
 
Fondazione Bruno Kessler
Resarch Intern
July 2019 – December 2019 Trento, Italy
Internship in automatic speech scoring for second language learner.

📰 Recent Publications

(2024). Automatic Subtitling and Subtitle Compression: FBK at the IWSLT 2024 Subtitling track. Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024).

Cite ACL Anthology Poster

(2024). SBAAM! Eliminating Transcript Dependency in Automatic Subtitling. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Cite ACL Anthology GitHub (Code and Models) GitHub (subSONAR) arXiv Poster Slides Video

(2024). SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation. Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024).

Cite ACL Anthology GitHub arXiv Poster

(2024). Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Cite ACL Anthology arXiv Poster Slides Video

(2024). StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Cite ACL Anthology GitHub arXiv Poster Slides Video

📌 Activities