Simone Merello — accepted AI-conference papers

2025

Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition

Niko Moritz, Ruiming Xie, Yashesh Gaur, Ke Li, Simone Merello, Zeeshan Ahmed +2

ICASSP 2025accepted

We propose the joint speech translation and recognition (JSTAR) model that leverages the fast-slow cascaded encoder architecture for simultaneous end-to-end automatic speech recognition (ASR) and speech translation (ST). The model is transducer-based and uses a multi-objective training strategy that…

Cited by 0 Source ↗Scholar ↗

2023

Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings

Mattia Atzeni, Mikhail Plekhanov, Frederic A Dreyer, Nora Kassner, Simone Merello, Louis Martin +1

EMNLP 2023long main

Entity linking methods based on dense retrieval are widely adopted in large-scale applications for their efficiency, but they can fall short of generative models, as they are sensitive to the structure of the embedding space. To address this issue, this paper introduces DUCK, an approach to infusing…

Cited by 0 Source ↗Scholar ↗