Marco Gaido

42 papers · 2020–2025 · 7 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (5) 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (54) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6) 🐝 Cross-Pollinator (14) 🌍 Conference Polyglot (7) 🏠 Conference Loyalist (20) 🤝 Dynamic Duo (40) 👥 Mega-Team (52) 🔬 Deep Specialist (21) 🧬 Topic Evolution 🏆 Keyword Champion (3) 🗃️ Keyword Collector (150) ⚡ Prolific Year (10) 🔥 Unstoppable (6) 💎 Century Club (42) ❓ The Questioner (8)

Conferences

ACL (20) EMNLP (8) IJCNLP (4) COLING (3) INTERSPEECH (3) NAACL (3) EACL (1)

Top co-authors

Matteo Negri (40) Luisa Bentivogli (24) Marco Turchi (22) Sara Papi (21) Mauro Cettolo (10) Beatrice Savoldi (9) Dennis Fucci (4) Alina Karakanta (4) Mohamed Nabih (2) Mattia A. Di Gangi (2)

Research topics

Linguistics (1)

Keywords

speech translation (24) machine translation (7) automatic speech recognition (6) speech recognition (4) speech-to-text translation (4) large language model (4) knowledge distillation (4) direct translation (4) speech foundation model (3) model compression (3) gender bia (3) direct model (3) neural machine translation (2) simultaneous speech translation (2) manual evaluation (2) simultaneous translation (2) speech encoder (2) named entity (2) automatic evaluation (2) attention mechanism (2)

Papers

Different Speech Translation Models Encode and Translate Speaker Gender Differently ACL 2025

Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison NAACL 2025

Findings of the WMT 2025 Shared Task on Model Compression: Early Insights on Compressing LLMs for Machine Translation EMNLP 2025

The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models EMNLP 2025

Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection COLING 2025

Findings of the IWSLT 2025 Evaluation Campaign ACL 2025

The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence ACL 2025

NUTSHELL: A Dataset for Abstract Generation from Scientific Talks ACL 2025

How Do Hyenas Deal with Human Speech? Speech Recognition and Translation with ConfHyena COLING 2024

When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP ACL 2024

SBAAM! Eliminating Transcript Dependency in Automatic Subtitling ACL 2024

StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection ACL 2024

Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing? ACL 2024

FBK@IWSLT Test Suites Task: Gender Bias evaluation with MuST-SHE ACL 2024

SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation ACL 2024

Automatic Subtitling and Subtitle Compression: FBK at the IWSLT 2024 Subtitling track ACL 2024

MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages EMNLP 2024

Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond INTERSPEECH 2024

Test Suites Task: Evaluation of Gender Fairness in MT with MuST-SHE and INES EMNLP 2023

Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection EMNLP 2023

Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023 ACL 2023

Joint Speech Translation and Named Entity Recognition INTERSPEECH 2023

Who Are We Talking About? Handling Person Names in Speech Translation ACL 2022

Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation ACL 2022

Does Simultaneous Speech Translation need Simultaneous Models? EMNLP 2022

On the Dynamics of Gender Learning in Speech Translation NAACL 2022

Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation NAACL 2022

Efficient yet Competitive Speech Translation: FBK@IWSLT2022 ACL 2022

CTC-based Compression for Direct Speech Translation EACL 2021

Is “moby dick” a Whale or a Bird? Named Entities and Terminology in Speech Translation EMNLP 2021

Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference? ACL 2021

Between Flexibility and Consistency: Joint Generation of Captions and Subtitles ACL 2021

Dealing with training and test segmentation mismatch: FBK@IWSLT2021 ACL 2021

How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation ACL 2021

Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference? IJCNLP 2021

How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation IJCNLP 2021

Dealing with training and test segmentation mismatch: FBK@IWSLT2021 IJCNLP 2021

Between Flexibility and Consistency: Joint Generation of Captions and Subtitles IJCNLP 2021

Speechformer: Reducing Information Loss in Direct Speech Translation EMNLP 2021

Breeding Gender-aware Direct Speech Translation Systems COLING 2020

Contextualized Translation of Automatically Segmented Speech INTERSPEECH 2020

End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020 ACL 2020