CVHCLGSep 13, 2024

An Efficient and Streaming Audio Visual Active Speaker Detection System

arXiv:2409.09018v1h-index: 5
Originality Incremental advance
AI Analysis

This work addresses practical deployment challenges for real-time ASD systems, which is incremental as it builds on existing architectures to improve efficiency.

The paper tackles the problem of high latency and memory usage in real-time Active Speaker Detection (ASD) systems by limiting the number of future and past context frames, achieving performance comparable to or better than state-of-the-art recurrent models with significantly reduced context frames.

This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant strides in improving network architectures and learning effective representations for ASD, a critical gap exists in the exploration of real-time system deployment. Existing models often suffer from high latency and memory usage, rendering them impractical for immediate applications. To bridge this gap, we present two scenarios that address the key challenges posed by real-time constraints. First, we introduce a method to limit the number of future context frames utilized by the ASD model. By doing so, we alleviate the need for processing the entire sequence of future frames before a decision is made, significantly reducing latency. Second, we propose a more stringent constraint that limits the total number of past frames the model can access during inference. This tackles the persistent memory issues associated with running streaming ASD systems. Beyond these theoretical frameworks, we conduct extensive experiments to validate our approach. Our results demonstrate that constrained transformer models can achieve performance comparable to or even better than state-of-the-art recurrent models, such as uni-directional GRUs, with a significantly reduced number of context frames. Moreover, we shed light on the temporal memory requirements of ASD systems, revealing that larger past context has a more profound impact on accuracy than future context. When profiling on a CPU we find that our efficient architecture is memory bound by the amount of past context it can use and that the compute cost is negligible as compared to the memory cost.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes