# CAST-ASD: Causal Attention over Speakers and Time for Online Active Speaker Detection

arXiv: https://arxiv.org/abs/2610.14676 · HTML: https://mlsanity.com/paper/2610.14676/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection](https://mlsanity.com/paper/2107.06592/) (2021)
- [AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection](https://mlsanity.com/paper/1901.01342/) (2019)
- [Voice Activity Projection: Self-supervised Learning of Turn-taking Events](https://mlsanity.com/paper/2205.09812/) (2022)
- [Active Speakers in Context](https://mlsanity.com/paper/2005.09812/) (2020)
- [A Light Weight Model for Active Speaker Detection](https://mlsanity.com/paper/2303.04439/) (2023)
- [MAAS: Multi-modal Assignation for Active Speaker Detection](https://mlsanity.com/paper/2101.03682/) (2021)
- [How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild](https://mlsanity.com/paper/2106.03932/) (2021)
- [EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments](https://mlsanity.com/paper/2107.04174/) (2021)
- [Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection](https://mlsanity.com/paper/2207.07783/) (2022)
- [UniCon: Unified Context Network for Robust Active Speaker Detection](https://mlsanity.com/paper/2108.02607/) (2021)
- [AVA-AVD: Audio-Visual Speaker Diarization in the Wild](https://mlsanity.com/paper/2111.14448/) (2021)
- [End-to-End Active Speaker Detection](https://mlsanity.com/paper/2203.14250/) (2022)
- [LoCoNet: Long-Short Context Network for Active Speaker Detection](https://mlsanity.com/paper/2301.08237/) (2023)
- [TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning](https://mlsanity.com/paper/2309.12306/) (2023)
- [Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering](https://mlsanity.com/paper/2507.18446/) (2025)
- [WASD: A Wilder Active Speaker Detection Dataset](https://mlsanity.com/paper/2303.05321/) (2023)
- [Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness](https://mlsanity.com/paper/2505.21954/) (2025)
- [Multimodal active speaker detection and virtual cinematography for video conferencing](https://mlsanity.com/paper/2002.03977/) (2020)
- [A Real-Time Active Speaker Detection System Integrating an Audio-Visual Signal with a Spatial Querying Mechanism](https://mlsanity.com/paper/2309.08295/) (2023)
- [Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings](https://mlsanity.com/paper/2502.06012/) (2025)
- [Dual-Stream Decoupled Learning for Temporal Consistency and Speaker Interaction in AVSD](https://mlsanity.com/paper/2512.19130/) (2025)
- [MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild](https://mlsanity.com/paper/2606.16731/) (2026)
- [An Efficient and Streaming Audio Visual Active Speaker Detection System](https://mlsanity.com/paper/2409.09018/) (2024)
- [GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection](https://mlsanity.com/paper/2512.15707/) (2025)

## Abstract (arXiv)

We present CAST-ASD (Causal Attention over Speakers and Time), a causal joint model for active speaker detection (ASD). Recent ASD models improve performance by jointly processing all faces in a scene, but operate offline, with the full clip available before any frame is labelled. Low-latency causal detectors instead process each face independently. CAST-ASD combines joint face reasoning with fully causal inference. It applies scene-level attention across faces within the current frame and causal temporal attention over each face's history, enabling information sharing across speakers with zero lookahead. Its parameter count does not grow with the number of faces. On MSDWild, where most negative face-frames contain a visible competing speaker, CAST-ASD reduces competing-speaker false alarms by 32% relative to the causal per-face detector it extends, with larger gains as scene occupancy increases. It outperforms all causal baselines on both validation splits while using only one-tenth the inter-speaker parameters of a three-block fixed-roster convolution. Code and models are available at https://github.com/prathamg007/CAST-ASD.