REVIEW 2 cited by
Voice Activity Projection: Self-supervised Learning of Turn-taking Events
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Voice Activity Projection: Self-supervised Learning of Turn-taking Events
read the original abstract
The modeling of turn-taking in dialog can be viewed as the modeling of the dynamics of voice activity of the interlocutors. We extend prior work and define the predictive task of Voice Activity Projection, a general, self-supervised objective, as a way to train turn-taking models without the need of labeled data. We highlight a theoretical weakness with prior approaches, arguing for the need of modeling the dependency of voice activity events in the projection window. We propose four zero-shot tasks, related to the prediction of upcoming turn-shifts and backchannels, and show that the proposed model outperforms prior work.
Forward citations
Cited by 2 Pith papers
-
Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction
Next-Turn introduces time-to-next-speech-onset prediction for duration-aware streaming endpoint detection, reporting a 25.9% improvement in accuracy within 320 ms.
-
Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders
Pretrained audio-visual speech encoders adapted with LoRA improve multimodal voice activity projection for turn-taking prediction across multiple languages and a robot mediation corpus.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.