Sara Papi

Researcher

    Short bio

    I am an AI Researcher at FBK (Fondazione Bruno Kessler), working on speech processing and multimodal LLMs within the MEETWEEN and DVPS Horizon European projects. I received my PhD cum laude in Information Engineering and Computer Science from the University of Trento in 2024, with a focus on simultaneous speech translation and subtitling. My research interests span multimodal and crosslingual instruction-following models, speech foundation models, and LLMs. My work has been recognized with awards, including the Best PhD Graduate 2024 Award in Information and Communication Technology from the University of Trento, an Outstanding Paper and SAC Award at ACL 2024, and a Social Impact Paper Award at EMNLP 2024. I actively contribute to the community as an organizer of the IWSLT Evaluation Campaign and as an Area Chair or reviewer for major conferences in speech and NLP, such as *ACL and Interspeech.

    Publications

    1. Papi, Sara; Züfle, Maike; Gaido, Marco; Savoldi, Beatrice; Liu, Danni; Douros, Ioannis; Bentivogli, Luisa; Niehues, Jan,
      MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks,
      in «»,
      The Fourteenth International Conference on Learning Representations,
      ,
      vol. ,
      n. ,
      2026
      , pp. -
    2. Lam, Tsz Kin; Gaido, Marco; Papi, Sara; Bentivogli, Luisa; Haddow, Barry,
      Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison,
      in «»,
      Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers),
      ,
      vol. ,
      n. ,
      2025
      , pp. 2994-
      3006
    3. Verdini, Francesco; Melucci, Pierfrancesco; Perna, Stefano; Cariaggi, Francesco; Gaido, Marco; Papi, Sara; Mazurek, Szymon; Kasztelnik, Marek; Bentivogli, Luisa; Bratières, Sebastien; Merialdo, Paolo; Scardapane, Simone,
      How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not,
      in «»,
      Proc. Interspeech 2025,
      ,
      vol. ,
      n. ,
      2025
      , pp. 1813-
      1817
    4. Papi, Sara; Gaido, Marco; Bentivogli, Luisa; Brutti, Alessio; Cettolo, Mauro; Gretter, Roberto; Matassoni, Marco; Nabih, Mohamed; Negri, Matteo,
      FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian,
      in «»,
      Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025),
      ,
      vol. ,
      n. ,
      2025
      , pp. -
    5. Gaido, Marco; Papi, Sara; Bentivogli, Luisa; Brutti, Alessio; Cettolo, Mauro; Gretter, Roberto; Matassoni, Marco; Nabih, Mohamed; Negri, Matteo,
      The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence,
      in «»,
      Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025),
      ,
      vol. ,
      n. ,
      2025
      , pp. 47-
      55
    6. Abdulmumin, Idris; Agostinelli, Victor; Alumäe, Tanel; Anastasopoulos, Antonios; Bentivogli, Luisa; Bojar, Ondřej; Borg, Claudia; Bougares, Fethi; Cattoni, Roldano; Cettolo, Mauro; Chen, Lizhong; Chen, William; Dabre, Raj; Estève, Yannick; Federico, Marcello; Fishel, Mark; Gaido, Marco; Javorský, Dávid; Kasztelnik, Marek; Kponou, Fortuné; Krubiński, Mateusz; Kin Lam, Tsz; Liu, Danni; Matusov, Evgeny; Kumar Maurya, Chandresh; P. Mccrae, John; Mdhaffar, Salima; Moslem, Yasmin; Murray, Kenton; Nakamura, Satoshi; Negri, Matteo; Niehues, Jan; Kr. Ojha, Atul; Ortega, John E.; Papi, Sara; Pecina, Pavel; Polák, Peter; Połeć, Piotr; Sankar, Ashwin; Savoldi, Beatrice; Sethiya, Nivedita; Sikasote, Claytone; Sperber, Matthias; Stüker, Sebastian; Sudoh, Katsuhito; Thompson, Brian; Turchi, Marco; Waibel, Alex; Wilken, Patrick; Zevallos, Rodolfo; Zouhar, Vilém; Züfle, Maike,
      Findings of the IWSLT 2025 Evaluation Campaign,
      in «»,
      Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025),
      ,
      vol. ,
      n. ,
      2025
      , pp. 412-
      481
    7. Züfle, Maike; Papi, Sara; Savoldi, Beatrice; Gaido, Marco; Bentivogli, Luisa; Niehues, Jan,
      NUTSHELL: A Dataset for Abstract Generation from Scientific Talks,
      in «»,
      Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025),
      ,
      vol. ,
      n. ,
      2025
      , pp. 19-
      32
    8. Rao Koluguri, Nithin; Sekoyan, Monica; Zelenfroynd, George; Meister, Sasha; Ding, Shuoyang; Kostandian, Sofia; Huang, He; Karpov, Nikolay; Balam, Jagadeesh; Lavrukhin, Vitaly; Peng, Yifan; Papi, Sara; Gaido, Marco; Brutti, Alessio; Ginsburg, Boris,
      Granary: Speech Recognition and Translation Dataset in 25 European Languages,
      in «»,
      Proceedings of Interspeech,
      ,
      vol. ,
      n. ,
      2025
      , pp. 3923-
      3927
    9. Papi, Sara; Polák, Peter; Macháček, Dominik; Bojar, Ondřej,
      How “Real” is Your Real-Time Simultaneous Speech-to-Text Translation System?,
      in «TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS»,
      ,
      ,
      vol. 13,
      n. ,
      2025
      , pp. 281-
      313
    10. Papi, Sara; Gaido, Marco; Negri, Matteo; Bentivogli, Luisa,
      SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation,
      in «»,
      Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024),
      ,
      vol. ,
      n. ,
      2024
      , pp. 72-
      79
    11. Cettolo, Mauro; Piergentili, Andrea; Papi, Sara; Gaido, Marco; Negri, Matteo; Bentivogli, Luisa,
      MAGNET - MAchines GeNErating Translations: A CALAMITA Challenge,
      in «»,
      Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024),
      ,
      vol. ,
      n. ,
      2024
      , pp. -
    12. Papi, Sara; Gaido, Marco; Pilzer, Andrea; Negri, Matteo,
      When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP,
      in «»,
      Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),
      ,
      vol. ,
      n. ,
      2024
      , pp. 3657-
      3672
    13. Ahmad, Ibrahim Said; Anastasopoulos, Antonios; Bojar, Ondřej; Borg, Claudia; Carpuat, Marine; Cattoni, Roldano; Cettolo, Mauro; Chen, William; Dong, Qianqian; Federico, Marcello; Haddow, Barry; Javorský, Dávid; Krubiński, Mateusz; Kim Lam, Tsz; Ma, Xutai; Mathur, Prashant; Matusov, Evgeny; Maurya, Chandresh; Mccrae, John; Murray, Kenton; Nakamura, Satoshi; Negri, Matteo; Niehues, Jan; Niu, Xing; Ojha, Atul Kr.; Ortega, John; Papi, Sara; Polák, Peter; Pospíšil, Adam; Pecina, Pavel; Salesky, Elizabeth; Sethiya, Nivedita; Sarkar, Balaram; Shi, Jiatong; Sikasote, Claytone; Sperber, Matthias; Stüker, Sebastian; Sudoh, Katsuhito; Thompson, Brian; Waibel, Alex; Watanabe, Shinji; Wilken, Patrick; Zemánek, Petr; Zevallos, Rodolfo,
      FINDINGS OF THE IWSLT 2024 EVALUATION CAMPAIGN,
      in «»,
      Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024),
      ,
      vol. ,
      n. ,
      2024
      , pp. 1-
      11
    14. Savoldi, Beatrice; Papi, Sara; Negri, Matteo; Guerberof-Arenas, Ana; Bentivogli, Luisa,
      What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study,
      in «»,
      Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing,
      ,
      vol. ,
      n. ,
      2024
      , pp. 18048-
      18076
    15. Gaido, Marco; Papi, Sara; Bentivogli, Luisa; Brutti, Alessio; Cettolo, Mauro; Gretter, Roberto; Matassoni, Marco; Nabih, Mohamed; Negri, Matteo,
      MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages,
      in «»,
      Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing,
      ,
      vol. ,
      n. ,
      2024
      , pp. 13934-
      13947
    16. Gaido, Marco; Papi, Sara; Negri, Matteo; Bentivogli, Luisa,
      Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?,
      in «»,
      Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),
      ,
      vol. ,
      n. ,
      2024
      , pp. 14760-
      14778
    17. Papi, Sara; Gaido, Marco; Negri, Matteo; Bentivogli, Luisa,
      StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection,
      in «»,
      Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),
      ,
      vol. ,
      n. ,
      2024
      , pp. 3692-
      3707
    18. Gaido, Marco; Papi, Sara; Negri, Matteo; Cettolo, Mauro; Bentivogli, Luisa,
      SBAAM! Eliminating Transcript Dependency in Automatic Subtitling,
      in «»,
      Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),
      ,
      vol. ,
      n. ,
      2024
      , pp. 3673-
      3691
    19. Gaido, Marco; Papi, Sara; Cettolo, Mauro; Cattoni, Roldano; Piergentili, Andrea; Negri, Matteo; Bentivogli, Luisa,
      Automatic Subtitling and Subtitle Compression: FBK at the IWSLT 2024 Subtitling track,
      in «»,
      Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024),
      ,
      vol. ,
      n. ,
      2024
      , pp. 86-
      96
    20. Papi, Sara; Wang, Peidong; Chen, Junkun; Xue, Jian; Kanda, Naoyuki; Li, Jinyu; Gaur, Yashesh,
      Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation,
      in «»,
      Proceedings of ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
      IEEE,
      vol. ,
      n. ,
      2024
      , pp. -
    21. Gaido, Marco; Papi, Sara; Negri, Matteo; Bentivogli, Luisa,
      How Do Hyenas Deal with Human Speech? Speech Recognition and Translation with ConfHyena,
      in «»,
      Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024),
      ,
      vol. ,
      n. ,
      2024
      , pp. 8184-
      8191
    22. Gaido, Marco; Papi, Sara; Negri, Matteo; Turchi, Marco,
      Joint Speech Translation and Named Entity Recognition,
      INTERSPEECH 2023,
      2023
      , pp. 47-
      51
    23. Papi, Sara; Negri, Matteo; Turchi, Marco,
      Attention as a Guide for Simultaneous Speech Translation,
      Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),
      2023
      , pp. 13340-
      13356
    24. Papi, Sara; Gaido, Marco; Negri, Matteo,
      Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023,
      Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023),
      2023
      , pp. 159-
      168
    25. Papi, Sara; Turchi, Marco; Negri, Matteo,
      AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation,
      INTERSPEECH 2023,
      2023
      , pp. 3974-
      3978
    26. Fucci, Dennis; Gaido, Marco; Papi, Sara; Cettolo, Mauro; Negri, Matteo; Bentivogli, Luisa,
      Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection,
      in «»,
      Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing,
      ,
      vol. ,
      n. ,
      2023
      , pp. 11505-
      11517
    27. Papi, Sara; Gaido, Marco; Karakanta, Alina; Cettolo, Mauro; Negri, Matteo; Turchi, Marco,
      Direct Speech Translation for Automatic Subtitling,
      in «TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS»,
      vol. 11,
      2023
      , pp. 1355-
      1376
    28. Papi, Sara; Wang, Peidon; Chen, Junku; Xue, Jian; Li, Jinyu; Gaur, Yashesh,
      Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments,
      Proceedings of 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU),
      2023
    29. Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco,
      Does Simultaneous Speech Translation need Simultaneous Models?,
      Findings of the Association for Computational Linguistics: EMNLP 2022,
      2022
      , pp. 141-
      153
    30. Papi, Sara; Karakanta, Alina; Negri, Matteo; Turchi, Marco,
      Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST Corpora,
      Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers),
      Association for Computational Linguistics,
      2022
      , pp. 480-
      487
    31. Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco,
      Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation,
      Proceedings of the Third Workshop on Automatic Simultaneous Translation,
      Association for Computational Linguistics,
      2022
      , pp. 12-
      17
    32. Gaido, Marco; Papi, Sara; Fucci, Dennis; Fiameni, Giuseppe; Negri, Matteo; Turchi, Marco,
      Efficient yet Competitive Speech Translation: FBK@IWSLT2022,
      in «»,
      Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022),
      Association for Computational Linguistics,
      vol. ,
      n. ,
      2022
      , pp. 177-
      189
    33. Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco,
      Dealing with training and test segmentation mismatch: FBK@IWSLT 2021,
      Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021),
      2021
      , pp. 84-
      91
    34. Karakanta, A.; Papi, S.; Negri, M.; Turchi, M.,
      Simultaneous speech translation for live subtitling: From delay to display,
      Proceedings of MT Summit 2021,
      2021
    35. Papi, S.; Negri, M.; Turchi, M.,
      Visualization: The missing factor in simultaneous speech translation,
      Proceedings of the Eighth Italian Conference on Computational Linguistics,
      vol. 3033,
      2021
    36. Papi, Sara; Gaido, Marco; Negri, Matteo; Turchi, Marco,
      Speechformer: Reducing Information Loss in Direct Speech Translation,
      Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing,
      2021
      , pp. 1698-
      1706
    37. Papi, Sara; Trentin, Edmondo; Gretter, Roberto; Matassoni, Marco; Falavigna, Daniele,
      Mixtures of Deep Neural Experts for Automated Speech Scoring,
      Proceedings of Interspeech 2020,
      2020
      , pp. 3845-
      3849

    MT Group at FBK Follow

    #MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai

    Avatar
    Retweet on Twitter MT Group at FBK Retweeted
    Avatar Marco Gaido @mgaido91 ·
    15 Apr

    🚀 New Shared Task: Model Compression for Machine Translation at #WMT2026 (co-located with #EMNLP2026)!
    📅 Test data out on June 18th, submissions by July 2nd!
    Can you shrink an LLM and keep translation quality high? 🧠🔧
    👉 https://www2.statmt.org/wmt26/model-compression.html #NLP #ML #LLM #ModelCompression

    Reply on Twitter 2044392295210828159 Retweet on Twitter 2044392295210828159 5 Like on Twitter 2044392295210828159 8 Twitter 2044392295210828159
    Avatar MT Group at FBK @fbk_mt ·
    9 Apr

    🎉We’re happy to welcome our new research engineer, Yiu Chung Leung, joining us to work on multimodal LLMs with a focus on speech. Excited for what’s ahead! 🚀

    Reply on Twitter 2042244043254432027 Retweet on Twitter 2042244043254432027 2 Like on Twitter 2042244043254432027 9 Twitter 2042244043254432027
    Retweet on Twitter MT Group at FBK Retweeted
    Avatar BeatriceSavoldi @beatricesavoldi ·
    7 Apr

    With @MalvinaNissim and @VivianaPatti, we've been teaching ethics in NLP as a hands-on course across Groningen, Pavia & Turin. We wrote up the experience and received the ✨Best Paper Award✨ at #EACL2026's TeachNLP Workshop. Huge thanks to the organizers and all our students!

    Reply on Twitter 2041435543037255751 Retweet on Twitter 2041435543037255751 4 Like on Twitter 2041435543037255751 13 Twitter 2041435543037255751
    Load More