Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Elmers, Mikey, Inoue, Koji, Lala, Divesh, Kawahara, Tatsuya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912624841588736
author Elmers, Mikey
Inoue, Koji
Lala, Divesh
Kawahara, Tatsuya
author_facet Elmers, Mikey
Inoue, Koji
Lala, Divesh
Kawahara, Tatsuya
contents Turn-taking is a fundamental component of spoken dialogue, however conventional studies mostly involve dyadic settings. This work focuses on applying voice activity projection (VAP) to predict upcoming turn-taking in triadic multi-party scenarios. The goal of VAP models is to predict the future voice activity for each speaker utilizing only acoustic data. This is the first study to extend VAP into triadic conversation. We trained multiple models on a Japanese triadic dataset where participants discussed a variety of topics. We found that the VAP trained on triadic conversation outperformed the baseline for all models but that the type of conversation affected the accuracy. This study establishes that VAP can be used for turn-taking in triadic dialogue scenarios. Future work will incorporate this triadic VAP turn-taking model into spoken dialogue systems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems
Elmers, Mikey
Inoue, Koji
Lala, Divesh
Kawahara, Tatsuya
Computation and Language
Turn-taking is a fundamental component of spoken dialogue, however conventional studies mostly involve dyadic settings. This work focuses on applying voice activity projection (VAP) to predict upcoming turn-taking in triadic multi-party scenarios. The goal of VAP models is to predict the future voice activity for each speaker utilizing only acoustic data. This is the first study to extend VAP into triadic conversation. We trained multiple models on a Japanese triadic dataset where participants discussed a variety of topics. We found that the VAP trained on triadic conversation outperformed the baseline for all models but that the type of conversation affected the accuracy. This study establishes that VAP can be used for turn-taking in triadic dialogue scenarios. Future work will incorporate this triadic VAP turn-taking model into spoken dialogue systems.
title Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems
topic Computation and Language
url https://arxiv.org/abs/2507.07518