Self-supervised learning (SSL) is at the origin of unprecedented improvements in many
different domains including computer vision and natural language processing. Speech …

We study phrase structure induction from visually-grounded speech. The core idea is to first
segment the speech waveform into sequences of word segments, and subsequently induce …

Past work on unsupervised parsing is constrained to written form. In this paper, we present
the first study on unsupervised spoken constituency parsing given unlabeled spoken …

Language is highly structured, with syntactic and semantic structures, to some extent,
agreed upon by speakers of the same language. With implicit or explicit awareness of such …

With deep representation learning advances, supervised dependency parsing has achieved
a notable enhancement. However, when the training data is drawn from various predefined …

Abstract Semantic Role Labeling (SRL), crucial for understanding semantic relationships in
sentences, has traditionally focused on text-based input. However, the increasing use of …

Traditional spoken language processing involves cascading an automatic speech
recognition (ASR) system into text processing models. In contrast," textless" methods …

We describe an approach to part-of-speech tagging from audio with very little human-
annotated data, for Highland Puebla Nahuatl, a low-resource language of Mexico. While …

We study phrase structure induction from visually-grounded speech without intermediate text
or text pre-trained models. The core idea is to first segment the speech waveform into …

PROPICTO is a project funded by the French National Research Agency and the Swiss
National Science Foundation, that aims at creating Speech-to-Pictograph translation …