← Search

Maxime Poli

2 accepted papers

2024

Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach

EMNLP 2024main

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal vocalizations. Modeling directly from speech opens up the path to m…