Marco Gaido

97 papers A* 2A 7B 2C 2Misc 2Journal 55Unranked 27
YearRankTypeTitle / Venue / Authors
2025 J jnl
Challenging the Abilities of Large Language Models in Italian: a Community Initiative.
CoRR
Malvina Nissim, Danilo Croce, Viviana Patti, Pierpaolo Basile, Giuseppe Attanasio, Elio Musacchio, Matteo Rinaldi, Federico Borazio, Maria Francis, Jacopo Gili, Daniel Scalena, Begoña Altuna, Ekhi Azurmendi, Valerio Basile, Luisa Bentivogli, Arianna Bisazza, Marianna Bolognesi, Dominique Brunato, Tommaso Caselli, Silvia Casola, Maria Cassese, Mauro Cettolo, Claudia Collacciani, Leonardo De Cosmo, Maria Pia di Buono, Andrea Esuli, Julen Etxaniz, Chiara Ferrando, Alessia Fidelangeli, Simona Frenda, Achille Fusco, Marco Gaido, Andrea Galassi, Federico Galli, Luca Giordano, Mattia Goffetti, Itziar Gonzalez-Dios, Lorenzo Gregori, Giulia Grundler, Sandro Iannaccone, Chunyang Jiang, Moreno La Quatra, Francesca Lagioia, Soda Marem Lo, Marco Madeddu, Bernardo Magnini, Raffaele Manna, Fabio Mercorio, Paola Merlo, Arianna Muti, Vivi Nastase, Matteo Negri, Dario Onorati, Elena Palmieri, Sara Papi, Lucia C. Passaro, Giulia Pensa, Andrea Piergentili, Daniele Potertì, Giovanni Puccetti, Federico Ranaldi, Leonardo Ranaldi, Andrea Amelio Ravelli, Martina Rosola, Elena Sofia Ruzzetti, Giuseppe Samo, Andrea Santilli, Piera Santin, Gabriele Sarti, Giovanni Sartor, Beatrice Savoldi, Antonio Serino, Andrea Seveso, Lucia Siciliani, Paolo Torroni, Rossella Varvara, Andrea Zaninello, Asya Zanollo, Fabio Massimo Zanzotto, Kamyar Zeinalipour, Andrea Zugarini
2025 J jnl
Cross-Attention is Half Explanation in Speech-to-Text Models.
CoRR
Sara Papi, Dennis Fucci, Marco Gaido, Matteo Negri, Luisa Bentivogli
2025 — conf
Different Speech Translation Models Encode and Translate Speaker Gender Differently.
ACL (2)
Dennis Fucci, Marco Gaido, Matteo Negri, Luisa Bentivogli, André F. T. Martins, Giuseppe Attanasio
2025 J jnl
Different Speech Translation Models Encode and Translate Speaker Gender Differently.
CoRR
Dennis Fucci, Marco Gaido, Matteo Negri, Luisa Bentivogli, André F. T. Martins, Giuseppe Attanasio
2025 A conf
Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution.
INTERSPEECH
Dennis Fucci, Marco Gaido, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2025 J jnl
Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution.
CoRR
Dennis Fucci, Marco Gaido, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2025 — conf
FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian.
CLiC-it
Sara Papi, Marco Gaido, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri
2025 J jnl
FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian.
CoRR
Sara Papi, Marco Gaido, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri
2025 A conf
Granary: Speech Recognition and Translation Dataset in 25 European Languages.
INTERSPEECH
Nithin Rao Koluguri, Monica Sekoyan, George Zelenfroynd, Sasha Meister, Shuoyang Ding, Sofia Kostandian, He Huang, Nikolay Karpov, Jagadeesh Balam, Vitaly Lavrukhin, Yifan Peng, Sara Papi, Marco Gaido, Alessio Brutti, Boris Ginsburg
2025 J jnl
Granary: Speech Recognition and Translation Dataset in 25 European Languages.
CoRR
Nithin Rao Koluguri, Monica Sekoyan, George Zelenfroynd, Sasha Meister, Shuoyang Ding, Sofia Kostandian, He Huang, Nikolay Karpov, Jagadeesh Balam, Vitaly Lavrukhin, Yifan Peng, Sara Papi, Marco Gaido, Alessio Brutti, Boris Ginsburg
2025 A conf
How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not.
INTERSPEECH
Francesco Verdini, Pierfrancesco Melucci, Stefano Perna, Francesco Cariaggi, Marco Gaido, Sara Papi, Szymon Mazurek, Marek Kasztelnik, Luisa Bentivogli, Sébastien Bratières, Paolo Merialdo, Simone Scardapane
2025 J jnl
How to Evaluate Speech Translation with Source-Aware Neural MT Metrics.
CoRR
Mauro Cettolo, Marco Gaido, Matteo Negri, Sara Papi, Luisa Bentivogli
2025 J jnl
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks.
CoRR
Sara Papi, Maike Züfle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues
2025 J jnl
NUTSHELL: A Dataset for Abstract Generation from Scientific Talks.
CoRR
Maike Züfle, Sara Papi, Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Jan Niehues
2025 — conf
Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison.
NAACL (Long Papers)
Tsz Kin Lam, Marco Gaido, Sara Papi, Luisa Bentivogli, Barry Haddow
2025 J jnl
Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison.
CoRR
Tsz Kin Lam, Marco Gaido, Sara Papi, Luisa Bentivogli, Barry Haddow
2025 J jnl
Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems.
CoRR
Marco Gaido, Sara Papi, Mauro Cettolo, Matteo Negri, Luisa Bentivogli
2025 B conf
Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection.
COLING
Beomseok Lee, Marco Gaido, Ioan Calapodescu, Laurent Besacier, Matteo Negri
2025 J jnl
The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models.
CoRR
Lina Conti, Dennis Fucci, Marco Gaido, Matteo Negri, Guillaume Wisniewski, Luisa Bentivogli
2025 J jnl
The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence.
CoRR
Marco Gaido, Sara Papi, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri
2025 J jnl
Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation.
CoRR
Lina Conti, Dennis Fucci, Marco Gaido, Matteo Negri, Guillaume Wisniewski, Luisa Bentivogli
2024 — conf
Direct Speech Translation Toward High-Quality, Inclusive, and Augmented Systems.
EAMT (1)
Marco Gaido
2024 — conf
Explainability for Speech Models: On the Challenges of Acoustic Feature Selection.
CLiC-it
Dennis Fucci, Beatrice Savoldi, Marco Gaido, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2024 — conf
How Do Hyenas Deal with Human Speech? Speech Recognition and Translation with ConfHyena.
LREC/COLING
Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli
2024 J jnl
How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena.
CoRR
Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli
2024 J jnl
How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not.
CoRR
Francesco Verdini, Pierfrancesco Melucci, Stefano Perna, Francesco Cariaggi, Marco Gaido, Sara Papi, Szymon Mazurek, Marek Kasztelnik, Luisa Bentivogli, Sébastien Bratières, Paolo Merialdo, Simone Scardapane
2024 — conf
MAGNET - MAchines GeNErating Translations: A CALAMITA Challenge.
CLiC-it
Mauro Cettolo, Andrea Piergentili, Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli
2024 A* conf
MOSEL: 950, 000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages.
EMNLP
Marco Gaido, Sara Papi, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri
2024 J jnl
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages.
CoRR
Marco Gaido, Sara Papi, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri
2024 — conf
SBAAM! Eliminating Transcript Dependency in Automatic Subtitling.
ACL (1)
Marco Gaido, Sara Papi, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2024 J jnl
SBAAM! Eliminating Transcript Dependency in Automatic Subtitling.
CoRR
Marco Gaido, Sara Papi, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2024 J jnl
SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation.
CoRR
Dennis Fucci, Marco Gaido, Beatrice Savoldi, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2024 J jnl
SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation.
CoRR
Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli
2024 J jnl
Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection.
CoRR
Beomseok Lee, Marco Gaido, Ioan Calapodescu, Laurent Besacier, Matteo Negri
2024 — conf
Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
ACL (1)
Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli
2024 J jnl
Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
CoRR
Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli
2024 A conf
Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond.
INTERSPEECH
Beomseok Lee, Ioan Calapodescu, Marco Gaido, Matteo Negri, Laurent Besacier
2024 J jnl
Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond.
CoRR
Beomseok Lee, Ioan Calapodescu, Marco Gaido, Matteo Negri, Laurent Besacier
2024 — conf
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection.
ACL (1)
Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli
2024 J jnl
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection.
CoRR
Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli
2024 — conf
When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP.
ACL (1)
Sara Papi, Marco Gaido, Andrea Pilzer, Matteo Negri
2023 — conf
Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023.
IWSLT@ACL
Sara Papi, Marco Gaido, Matteo Negri
2023 J jnl
Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023.
CoRR
Sara Papi, Marco Gaido, Matteo Negri
2023 J jnl
Direct Speech Translation for Automatic Subtitling.
Trans. Assoc. Comput. Linguistics
Sara Papi, Marco Gaido, Alina Karakanta, Mauro Cettolo, Matteo Negri, Marco Turchi
2023 J jnl
Distributed Silhouette Algorithm: Evaluating Clustering on Big Data.
CoRR
Marco Gaido
2023 — conf
How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation.
CLiC-it
Marco Gaido, Dennis Fucci, Matteo Negri, Luisa Bentivogli
2023 J jnl
How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation.
CoRR
Marco Gaido, Dennis Fucci, Matteo Negri, Luisa Bentivogli
2023 A* conf
Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection.
EMNLP
Dennis Fucci, Marco Gaido, Sara Papi, Mauro Cettolo, Matteo Negri, Luisa Bentivogli
2023 J jnl
Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection.
CoRR
Dennis Fucci, Marco Gaido, Sara Papi, Mauro Cettolo, Matteo Negri, Luisa Bentivogli
2023 A conf
Joint Speech Translation and Named Entity Recognition.
INTERSPEECH
Marco Gaido, Sara Papi, Matteo Negri, Marco Turchi
2023 Misc conf
Named Entity Detection and Injection for Direct Speech Translation.
ICASSP
Marco Gaido, Yun Tang, Ilia Kulikov, Rongqing Huang, Hongyu Gong, Hirofumi Inaguma
2023 C conf
No Pitch Left Behind: Addressing Gender Unbalance In Automatic Speech Recognition Through Pitch Manipulation.
ASRU
Dennis Fucci, Marco Gaido, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2023 J jnl
No Pitch Left Behind: Addressing Gender Unbalance in Automatic Speech Recognition through Pitch Manipulation.
CoRR
Dennis Fucci, Marco Gaido, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
2023 J jnl
Reproducibility is Nothing without Correctness: The Importance of Testing Code in NLP.
CoRR
Sara Papi, Marco Gaido, Andrea Pilzer, Matteo Negri
2023 — conf
Test Suites Task: Evaluation of Gender Fairness in MT with MuST-SHE and INES.
WMT
Beatrice Savoldi, Marco Gaido, Matteo Negri, Luisa Bentivogli
2023 J jnl
Test Suites Task: Evaluation of Gender Fairness in MT with MuST-SHE and INES.
CoRR
Beatrice Savoldi, Marco Gaido, Matteo Negri, Luisa Bentivogli
2022 J jnl
Direct Speech Translation for Automatic Subtitling.
CoRR
Sara Papi, Marco Gaido, Alina Karakanta, Mauro Cettolo, Matteo Negri, Marco Turchi
2022 — conf
Does Simultaneous Speech Translation need Simultaneous Models?
EMNLP (Findings)
Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi
2022 J jnl
Does Simultaneous Speech Translation need Simultaneous Models?
CoRR
Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi
2022 — conf
Efficient yet Competitive Speech Translation: FBK@IWSLT2022.
IWSLT@ACL
Marco Gaido, Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri, Marco Turchi
2022 J jnl
Efficient yet Competitive Speech Translation: FBK@IWSLT2022.
CoRR
Marco Gaido, Sara Papi, Dennis Fucci, Giuseppe Fiameni, Matteo Negri, Marco Turchi
2022 C conf
Extending the MuST-C Corpus for a Comparative Evaluation of Speech Translation Technology.
EAMT
Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta, Matteo Negri, Marco Turchi
2022 J jnl
Joint Speech Translation and Named Entity Recognition.
CoRR
Marco Gaido, Sara Papi, Matteo Negri, Marco Turchi
2022 J jnl
Named Entity Detection and Injection for Direct Speech Translation.
CoRR
Marco Gaido, Yun Tang, Ilia Kulikov, Rongqing Huang, Hongyu Gong, Hirofumi Inaguma
2022 J jnl
Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation.
CoRR
Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi
2022 — conf
Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation.
ACL (1)
Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, Marco Turchi
2022 J jnl
Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation.
CoRR
Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, Marco Turchi
2022 — conf
Who Are We Talking About? Handling Person Names in Speech Translation.
IWSLT@ACL
Marco Gaido, Matteo Negri, Marco Turchi
2022 J jnl
Who Are We Talking About? Handling Person Names in Speech Translation.
CoRR
Marco Gaido, Matteo Negri, Marco Turchi
2021 — conf
Between Flexibility and Consistency: Joint Generation of Captions and Subtitles.
IWSLT
Alina Karakanta, Marco Gaido, Matteo Negri, Marco Turchi
2021 J jnl
Between Flexibility and Consistency: Joint Generation of Captions and Subtitles.
CoRR
Alina Karakanta, Marco Gaido, Matteo Negri, Marco Turchi
2021 — conf
Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation.
ICNLSP
Marco Gaido, Matteo Negri, Mauro Cettolo, Marco Turchi
2021 J jnl
Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation.
CoRR
Marco Gaido, Matteo Negri, Mauro Cettolo, Marco Turchi
2021 A conf
CTC-based Compression for Direct Speech Translation.
EACL
Marco Gaido, Mauro Cettolo, Matteo Negri, Marco Turchi
2021 J jnl
CTC-based Compression for Direct Speech Translation.
CoRR
Marco Gaido, Mauro Cettolo, Matteo Negri, Marco Turchi
2021 — conf
Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?
ACL/IJCNLP (1)
Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta, Alberto Martinelli, Matteo Negri, Marco Turchi
2021 J jnl
Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?
CoRR
Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta, Alberto Martinelli, Matteo Negri, Marco Turchi
2021 — conf
Dealing with training and test segmentation mismatch: FBK@IWSLT2021.
IWSLT
Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi
2021 J jnl
Dealing with training and test segmentation mismatch: FBK@IWSLT2021.
CoRR
Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi
2021 J jnl
Gender Bias in Machine Translation.
CoRR
Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, Marco Turchi
2021 J jnl
Gender Bias in Machine Translation.
Trans. Assoc. Comput. Linguistics
Beatrice Savoldi, Marco Gaido, Luisa Bentivogli, Matteo Negri, Marco Turchi
2021 — conf
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation.
ACL/IJCNLP (Findings)
Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi
2021 J jnl
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation.
CoRR
Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi
2021 — conf
Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translation.
EMNLP (1)
Marco Gaido, Susana Rodríguez, Matteo Negri, Luisa Bentivogli, Marco Turchi
2021 J jnl
Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translation.
CoRR
Marco Gaido, Susana Rodríguez, Matteo Negri, Luisa Bentivogli, Marco Turchi
2021 — conf
Speechformer: Reducing Information Loss in Direct Speech Translation.
EMNLP (1)
Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi
2021 J jnl
Speechformer: Reducing Information Loss in Direct Speech Translation.
CoRR
Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi
2020 B conf
Breeding Gender-aware Direct Speech Translation Systems.
COLING
Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi
2020 J jnl
Breeding Gender-aware Direct Speech Translation Systems.
CoRR
Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, Marco Turchi
2020 A conf
Contextualized Translation of Automatically Segmented Speech.
INTERSPEECH
Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Mauro Cettolo, Marco Turchi
2020 J jnl
Contextualized Translation of Automatically Segmented Speech.
CoRR
Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Mauro Cettolo, Marco Turchi
2020 — conf
End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020.
IWSLT
Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Marco Turchi
2020 J jnl
End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020.
CoRR
Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Marco Turchi
2020 — conf
On Knowledge Distillation for Direct Speech Translation.
CLiC-it
Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Marco Turchi
2020 J jnl
On Knowledge Distillation for Direct Speech Translation.
CoRR
Marco Gaido, Mattia Antonino Di Gangi, Matteo Negri, Marco Turchi
2020 Misc conf
On Target Segmentation for Direct Speech Translation.
AMTA
Mattia Antonino Di Gangi, Marco Gaido, Matteo Negri, Marco Turchi
2020 J jnl
On Target Segmentation for Direct Speech Translation.
CoRR
Mattia Antonino Di Gangi, Marco Gaido, Matteo Negri, Marco Turchi