collaborators

7 papers

eess.AS2026

Bootstrapping Audiovisual Speech Recognition in Zero-AV-Resource Scenarios with Synthetic Visual Data

Pol Buitrago, Pol GÃ lvez, Oriol Pareras +1

Audiovisual speech recognition (AVSR) combines acoustic and visual cues to improve transcription robustness under challenging conditions but remains out of reach for most under-res…

eess.AS2026

Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks

Pol Buitrago, Oriol Pareras, Federico Costa +1

Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely on extralinguistic acoustic cues rather than lexical content. However, prior studies rep…

cs.CL2026

Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?

Oriol Pareras, Gerard I. Gállego, Gerard I. Gállego +4

Recent work on Speech-to-Text Translation (S2TT) has focused on LLM-based models, introducing the increasingly adopted Chain-of-Thought (CoT) prompting, where the model is guided t…

cs.CL2025

Listening or Reading? Evaluating Speech Awareness in Chain-of-Thought Speech-to-Text Translation

Jacobo Romero-Díaz, Jacobo Romero-Díaz, Gerard I. Gállego +6

Speech-to-Text Translation (S2TT) systems built from Automatic Speech Recognition (ASR) and Text-to-Text Translation (T2TT) modules face two major limitations: error propagation an…

cs.CL2025

Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios

Gerard I. Gállego, Gerard I. Gállego, Oriol Pareras +4

We propose a Speech-to-Text Translation (S2TT) approach that integrates phoneme representations into a Chain-of-Thought (CoT) framework to improve translation in low-resource and z…

cs.CV2025

Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization

Iñigo Pikabea, Iñaki Lacunza, Oriol Pareras +4

Rapid advancements in Visual Language Models (VLMs) have transformed multimodal understanding but are often constrained by generating English responses regardless of the input lang…