# Online Audio-Visual Autoregressive Speaker Extraction

arXiv: https://arxiv.org/abs/2506.01270 · HTML: https://mlsanity.com/paper/2506.01270/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2025.

## Built on by (most cited first, 1 of 1)

- [Adapting Personalized Speech Enhancement for Low-Latency Audio-Visual Target-Speaker Extraction](https://mlsanity.com/paper/2609.30631/) (2026)

## Abstract (arXiv)

This paper proposes a novel online audio-visual speaker extraction model. In the streaming regime, most studies optimize the audio network only, leaving the visual frontend less explored. We first propose a lightweight visual frontend based on depth-wise separable convolution. Then, we propose a lightweight autoregressive acoustic encoder to serve as the second cue, to actively explore the information in the separated speech signal from past steps. Scenario-wise, for the first time, we study how the algorithm performs when there is a change in focus of attention, i.e., the target speaker. Experimental results on LRS3 datasets show that our visual frontend performs comparably to the previous state-of-the-art on both SkiM and ConvTasNet audio backbones with only 0.1 million network parameters and 2.1 MACs per second of processing. The autoregressive acoustic encoder provides an additional 0.9 dB gain in terms of SI-SNRi, and its momentum is robust against the change in attention.