Salvato in:
Dettagli Bibliografici
Autori principali: Saga, Takeshi, Pelachaud, Catherine
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.03980
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910987002576896
author Saga, Takeshi
Pelachaud, Catherine
author_facet Saga, Takeshi
Pelachaud, Catherine
contents Turn-taking management is crucial for any social interaction. Still, it is challenging to model human-machine interaction due to the complexity of the social context and its multimodal nature. Unlike conventional systems based on silence duration, previous existing voice activity projection (VAP) models successfully utilized a unified representation of turn-taking behaviors as prediction targets, which improved turn-taking prediction performance. Recently, a multimodal VAP model outperformed the previous state-of-the-art model by a significant margin. In this paper, we propose a multimodal model enhanced with pre-trained audio and face encoders to improve performance by capturing subtle expressions. Our model performed competitively, and in some cases, even better than state-of-the-art models on turn-taking metrics. All the source codes and pretrained models are available at https://github.com/sagatake/VAPwithAudioFaceEncoders.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03980
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Voice Activity Projection Model with Multimodal Encoders
Saga, Takeshi
Pelachaud, Catherine
Computation and Language
Turn-taking management is crucial for any social interaction. Still, it is challenging to model human-machine interaction due to the complexity of the social context and its multimodal nature. Unlike conventional systems based on silence duration, previous existing voice activity projection (VAP) models successfully utilized a unified representation of turn-taking behaviors as prediction targets, which improved turn-taking prediction performance. Recently, a multimodal VAP model outperformed the previous state-of-the-art model by a significant margin. In this paper, we propose a multimodal model enhanced with pre-trained audio and face encoders to improve performance by capturing subtle expressions. Our model performed competitively, and in some cases, even better than state-of-the-art models on turn-taking metrics. All the source codes and pretrained models are available at https://github.com/sagatake/VAPwithAudioFaceEncoders.
title Voice Activity Projection Model with Multimodal Encoders
topic Computation and Language
url https://arxiv.org/abs/2506.03980