Scaling Up Adaptive Filter Optimizers

TL;DR

This paper presents SMS-AF, a scalable online adaptive filtering method using neural networks, which improves performance on acoustic echo cancellation and speech enhancement tasks while maintaining real-time processing.

Contribution

Introduction of SMS-AF, a neural network-based adaptive filtering method that scales performance with compute, including new features like pruning and multi-step optimization.

Findings

Performance scales with inference cost and model size.

Achieves multi-dB gains in echo cancellation and speech enhancement.

Operates in real-time on a single CPU core.

Abstract

We introduce a new online adaptive filtering method called supervised multi-step adaptive filters (SMS-AF). Our method uses neural networks to control or optimize linear multi-delay or multi-channel frequency-domain filters and can flexibly scale-up performance at the cost of increased compute -- a property rarely addressed in the AF literature, but critical for many applications. To do so, we extend recent work with a set of improvements including feature pruning, a supervised loss, and multiple optimization steps per time-frame. These improvements work in a cohesive manner to unlock scaling. Furthermore, we show how our method relates to Kalman filtering and meta-adaptive filtering, making it seamlessly applicable to a diverse set of AF tasks. We evaluate our method on acoustic echo cancellation (AEC) and multi-channel speech enhancement tasks and compare against several baselines on standard synthetic and real-world datasets. Results show our method performance scales with inference cost and model capacity, yields multi-dB performance gains for both tasks, and is real-time capable on a single CPU core.