Pith. sign in

How Much Does Prosody Help Turn-taking? Investigations using Voice Activity Projection Models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Turn-taking is a fundamental aspect of human communication and can be described as the ability to take turns, project upcoming turn shifts, and supply backchannels at appropriate locations throughout a conversation. In this work, we investigate the role of prosody in turn-taking using the recently proposed Voice Activity Projection model, which incrementally models the upcoming speech activity of the interlocutors in a self-supervised manner, without relying on explicit annotation of turn-taking events, or the explicit modeling of prosodic features. Through manipulation of the speech signal, we investigate how these models implicitly utilize prosodic information. We show that these systems learn to utilize various prosodic aspects of speech both on aggregate quantitative metrics of long-form conversations and on single utterances specifically designed to depend on prosody.

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Real-Time Textless Dialogue Generation

cs.CL · 2025-01-08 · conditional · novelty 4.0

A streaming, textless dialogue model predicts turn-taking actions every 160 ms and generates speech units, improving naturalness over cascaded systems at the cost of lower semantic coherence.

citing papers explorer

Showing 1 of 1 citing paper.

  • Real-Time Textless Dialogue Generation cs.CL · 2025-01-08 · conditional · none · ref 7 · internal anchor

    A streaming, textless dialogue model predicts turn-taking actions every 160 ms and generates speech units, improving naturalness over cascaded systems at the cost of lower semantic coherence.