@inproceedings{ea7ab4f1d5f04f5a9ed66316e672cb16,
title = "Toward Real Time Word Based Prosody Recognition",
abstract = "Prosodic salience is a heuristic based on word-level prosody in child-directed speech that is thought to serve as a cue for attentional focus. It has been used in the context of robotic language acquisition to extract the contextually most relevant words from a human tutor{\textquoteright}s speech to ground them in a robot{\textquoteright}s sensorimotor data. However, the pipeline for performing word-based prosody-recognition operated in a semi-automatic manner and required substantial manual effort. We describe our efforts to automate the existing pipeline by including real time prosody recognition, and a modern speech recognition and forced alignment model. The intention is to enable its use in real time for human-in-the-loop robotic language acquisition and other socially driven forms of online learning.",
author = "Alex Tilson and Frank Foerster",
note = "{\textcopyright} 2024 Association for Computational Linguistics. This work is distributed under the terms of the Creative Commons Attribution License (CC BY), https://creativecommons.org/licenses/by/4.0/ ; 2024 CLASP Conference on Multimodality and Interaction in Language Learning, MILLing 2024 ; Conference date: 14-10-2024 Through 15-10-2024",
year = "2024",
month = dec,
day = "30",
language = "English",
isbn = "979-8-89176-163-6",
volume = "3",
series = "CLASP Conference Proceedings",
publisher = "Association for Computational Linguistics",
pages = "62--67",
editor = "Amy Qiu and Bill Noble and David Pagmar and Vladislav Maraev and Nikolai Ilinykh",
booktitle = "Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning",
}