Publications

Sara Papi, Marco Gaido, Andrea Pilzer, Matteo Negri (2024). When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Cite ACL Anthology GitHub (Pangolinn) GitHub (Case Study) arXiv Poster Slides Video

Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli (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

Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli (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

Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli (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

Marco Gaido, Sara Papi, Matteo Negri, Mauro Cettolo, Luisa Bentivogli (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

Marco Gaido, Sara Papi, Mauro Cettolo, Roldano Cattoni, Andrea Piergentili, Matteo Negri, Luisa Bentivogli (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

Sara Papi, Peidong Wang, Junkun Chen, Jian Xue, Naoyuki Kanda, Jinyu Li, Yashesh Gaur (2024). Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cite DOI Poster

Dennis Fucci, Marco Gaido, Sara Papi, Mauro Cettolo, Matteo Negri, Luisa Bentivogli (2023). Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.

Cite URL Slides Video

Marco Gaido, Sara Papi, Matteo Negri, Marco Turchi (2023). Joint Speech Translation and Named Entity Recognition. INTERSPEECH 2023.

Cite DOI URL

Sara Papi, Marco Turchi, Matteo Negri (2023). AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation. INTERSPEECH 2023.

Cite DOI URL Poster

Sara Papi, Peidong Wang, Junkun Chen, Jian Xue, Jinyu Li, Yashesh Gaur (2023). Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments. 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Cite DOI Poster Video

Sara Papi, Marco Gaido, Matteo Negri (2023). Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023. Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023).

Cite DOI URL Poster

Sara Papi, Matteo Negri, Marco Turchi (2023). Attention as a Guide for Simultaneous Speech Translation. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Cite DOI URL Poster Slides Video

Sara Papi, Alina Karakanta, Matteo Negri, Marco Turchi (2022). 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).

Cite URL Poster Video

Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi (2022). Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation. Proceedings of the Third Workshop on Automatic Simultaneous Translation.

Cite DOI URL Slides

Marco Gaido, Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri, Marco Turchi (2022). Efficient yet Competitive Speech Translation: FBK@IWSLT2022. Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022).

Cite DOI URL Poster Slides

Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi (2022). Does Simultaneous Speech Translation need Simultaneous Models?. Findings of the Association for Computational Linguistics: EMNLP 2022.

Cite DOI URL Poster Slides Video

Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi (2021). Speechformer: Reducing Information Loss in Direct Speech Translation. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.

Cite DOI URL Poster Slides Video

Alina Karakanta, Sara Papi, Matteo Negri, Marco Turchi (2021). Simultaneous Speech Translation for Live Subtitling: from Delay to Display. Proceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW).

Cite URL

Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi (2021). Dealing with training and test segmentation mismatch: FBK@IWSLT2021. Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021).

Cite DOI URL Slides

Sara Papi, Edmondo Trentin, Roberto Gretter, Marco Matassoni, Daniele Falavigna (2020). Mixtures of Deep Neural Experts for Automated Speech Scoring. Proc. Interspeech 2020.

Cite DOI