Search Results for author: Nicolas Hamilakis

Found 3 papers, 1 papers with code

Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge

no code implementations27 Oct 2022 Ewan Dunbar, Nicolas Hamilakis, Emmanuel Dupoux

Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as phonemes, dictionaries or parse trees.

Acoustic Unit Discovery Language Modelling +1

The Zero Resource Speech Challenge 2021: Spoken language modelling

no code implementations29 Apr 2021 Ewan Dunbar, Mathieu Bernard, Nicolas Hamilakis, Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé, Morgane Rivière, Eugene Kharitonov, Emmanuel Dupoux

We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.