Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio content

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Uro, Rémi, Tahon, Marie, Doukhan, David, Laurent, Antoine, Rilliard, Albert
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929386701193216
author Uro, Rémi
Tahon, Marie
Doukhan, David
Laurent, Antoine
Rilliard, Albert
author_facet Uro, Rémi
Tahon, Marie
Doukhan, David
Laurent, Antoine
Rilliard, Albert
contents Transition Relevance Places are defined as the end of an utterance where the interlocutor may take the floor without interrupting the current speaker --i.e., a place where the turn is terminal. Analyzing turn terminality is useful to study the dynamic of turn-taking in spontaneous conversations. This paper presents an automatic classification of spoken utterances as Terminal or Non-Terminal in multi-speaker settings. We compared audio, text, and fusions of both approaches on a French corpus of TV and Radio extracts annotated with turn-terminality information at each speaker change. Our models are based on pre-trained self-supervised representations. We report results for different fusion strategies and varying context sizes. This study also questions the problem of performance variability by analyzing the differences in results for multiple training runs with random initialization. The measured accuracy would allow the use of these models for large-scale analysis of turn-taking.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10073
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio content
Uro, Rémi
Tahon, Marie
Doukhan, David
Laurent, Antoine
Rilliard, Albert
Audio and Speech Processing
Computation and Language
Human-Computer Interaction
Sound
Transition Relevance Places are defined as the end of an utterance where the interlocutor may take the floor without interrupting the current speaker --i.e., a place where the turn is terminal. Analyzing turn terminality is useful to study the dynamic of turn-taking in spontaneous conversations. This paper presents an automatic classification of spoken utterances as Terminal or Non-Terminal in multi-speaker settings. We compared audio, text, and fusions of both approaches on a French corpus of TV and Radio extracts annotated with turn-terminality information at each speaker change. Our models are based on pre-trained self-supervised representations. We report results for different fusion strategies and varying context sizes. This study also questions the problem of performance variability by analyzing the differences in results for multiple training runs with random initialization. The measured accuracy would allow the use of these models for large-scale analysis of turn-taking.
title Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio content
topic Audio and Speech Processing
Computation and Language
Human-Computer Interaction
Sound
url https://arxiv.org/abs/2406.10073