# Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs

arXiv: https://arxiv.org/abs/1808.10785 · HTML: https://mlsanity.com/paper/1808.10785/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2018.

## Built on by (most cited first, 12 of 12)

- [Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion](https://mlsanity.com/paper/2401.14717/) (2024)
- [Visual Cues Enhance Predictive Turn-Taking for Two-Party Human Interaction](https://mlsanity.com/paper/2505.21043/) (2025)
- [It's not what you said, it's how you said it: discriminative perception of speech as a multichannel communication system](https://mlsanity.com/paper/2105.00260/) (2021)
- [Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue](https://mlsanity.com/paper/2603.11409/) (2026)
- [3M-TRANSFORMER: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction](https://mlsanity.com/paper/2310.14859/) (2023)
- [MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild](https://mlsanity.com/paper/2606.16731/) (2026)
- [Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay](https://mlsanity.com/paper/2503.16432/) (2025)
- [Syn-TurnTurk: A Synthetic Dataset for Turn-Taking Prediction in Turkish Dialogues](https://mlsanity.com/paper/2604.13620/) (2026)
- [Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio content](https://mlsanity.com/paper/2406.10073/) (2024)
- [Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings](https://mlsanity.com/paper/2606.17542/) (2026)
- [Real-TurnTurk: A Multimodal Turkish Corpus for Turn-Taking Prediction](https://mlsanity.com/paper/2608.22071/) (2026)
- [Less can be More: What Aspects of Speech Drive End-of-Turn Detection](https://mlsanity.com/paper/2609.11066/) (2026)

## Abstract (arXiv)

In human conversational interactions, turn-taking exchanges can be coordinated using cues from multiple modalities. To design spoken dialog systems that can conduct fluid interactions it is desirable to incorporate cues from separate modalities into turn-taking models. We propose that there is an appropriate temporal granularity at which modalities should be modeled. We design a multiscale RNN architecture to model modalities at separate timescales in a continuous manner. Our results show that modeling linguistic and acoustic features at separate temporal rates can be beneficial for turn-taking modeling. We also show that our approach can be used to incorporate gaze features into turn-taking models.