Gerard I. Gállego

Universitat Politècnica de Catalunya — Spain

Computer Science · Physical Sciences

9h-index189citations38works1.12yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Natural Language Processing Techniques(26), Speech Recognition and Synthesis(19), Topic Modeling(16), Music and Audio Processing(7), Hand Gesture Recognition Systems(4)

Publications38 total

Listening or Reading? Evaluating Speech Awareness in Chain-of-Thought Speech-to-Text Translation
arXiv (Cornell University)·2025Open Access
Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?
arXiv (Cornell University)·2025Open Access
Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios
2025· 1 citedOpen Access
Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation
2025
Unveiling the Role of Pretraining in Direct Speech Translation
arXiv (Cornell University)·2024Open Access
Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation
arXiv (Cornell University)·2024Open Access
Pushing the Limits of Zero-shot End-to-End Speech Translation
arXiv (Cornell University)·2024Open Access
Unveiling the Role of Pretraining in Direct Speech Translation
2024Open Access
Pushing the Limits of Zero-shot End-to-End Speech Translation
2024· 9 citedOpen Access
SpeechAlign: a Framework for Speech Translation Alignment Evaluation
arXiv (Cornell University)·2023Open Access
Sign Language Translation from Instructional Videos
2023· 10 citedOpen Access
Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23
arXiv (Cornell University)·2023Open Access
Sign Language Translation from Instructional Videos
2023· 14 cited
Explaining How Transformers Use Context to Build Predictions
arXiv (Cornell University)·2023· 1 citedOpen Access
Efficient Speech Translation with Dynamic Latent Perceivers
2023· 1 citedOpen Access
Sign Language Translation from Instructional Videos
arXiv (Cornell University)·2023· 1 citedOpen Access
Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23
2023· 1 citedOpen Access
Explaining How Transformers Use Context to Build Predictions
2023· 9 citedOpen Access
Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22
arXiv (Cornell University)·2022· 4 citedOpen Access
Efficient Speech Translation with Dynamic Latent Perceivers
arXiv (Cornell University)·2022· 1 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Marta R. Costa‐jussà(29), Ioannis Tsiamas(15), José A. R. Fonollosa(11), Javier Ferrando(8), Carlos Escolano(7), Belen Alastruey(4), Jordi Torres(4), Xavier Giró-i-Nieto(4), Belen Alastruey(4), Laia Tarrés(3), Amanda Duarte(3), Oriol Pareras(3), José Fonollosa(2), Christine Basta(2), Gerard Sant(2), Javier Hernando(2), Roy Fejgin(2), Chunghsin Yeh(2), Xiaoyu Liu(2), Gautam Bhattacharya(2)