Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pupier, Adrien, Coavoux, Maximin, Goulian, Jérôme, Lecouteux, Benjamin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909226855563264
author Pupier, Adrien
Coavoux, Maximin
Goulian, Jérôme
Lecouteux, Benjamin
author_facet Pupier, Adrien
Coavoux, Maximin
Goulian, Jérôme
Lecouteux, Benjamin
contents Direct dependency parsing of the speech signal -- as opposed to parsing speech transcriptions -- has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing the limitations of a pipeline approach that would consist of using first an Automatic Speech Recognition (ASR) system and then a syntactic parser. In this article, we report on a set of experiments aiming at assessing the performance of two parsing paradigms (graph-based parsing and sequence labeling based parsing) on speech parsing. We perform this evaluation on a large treebank of spoken French, featuring realistic spontaneous conversations. Our findings show that (i) the graph based approach obtain better results across the board (ii) parsing directly from speech outperforms a pipeline approach, despite having 30% fewer parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech
Pupier, Adrien
Coavoux, Maximin
Goulian, Jérôme
Lecouteux, Benjamin
Computation and Language
Direct dependency parsing of the speech signal -- as opposed to parsing speech transcriptions -- has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing the limitations of a pipeline approach that would consist of using first an Automatic Speech Recognition (ASR) system and then a syntactic parser. In this article, we report on a set of experiments aiming at assessing the performance of two parsing paradigms (graph-based parsing and sequence labeling based parsing) on speech parsing. We perform this evaluation on a large treebank of spoken French, featuring realistic spontaneous conversations. Our findings show that (i) the graph based approach obtain better results across the board (ii) parsing directly from speech outperforms a pipeline approach, despite having 30% fewer parameters.
title Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech
topic Computation and Language
url https://arxiv.org/abs/2406.12621