Hybrid Neural Networks for On-device Directional Hearing

TL;DR

This paper introduces DeepBeam, a hybrid neural network model that combines traditional beamformers with lightweight neural nets to enable real-time, low-latency directional hearing on wearable devices, achieving significant reductions in computational resources.

Contribution

DeepBeam is a novel hybrid model that improves efficiency and generalizability for on-device directional hearing by combining traditional beamformers with a custom neural network.

Findings

Comparable performance to state-of-the-art models on synthetic data

5x reduction in model size and computation

Real-time operation at 8 ms on low-power CPUs

Abstract

On-device directional hearing requires audio source separation from a given direction while achieving stringent human-imperceptible latency requirements. While neural nets can achieve significantly better performance than traditional beamformers, all existing models fall short of supporting low-latency causal inference on computationally-constrained wearables. We present DeepBeam, a hybrid model that combines traditional beamformers with a custom lightweight neural net. The former reduces the computational burden of the latter and also improves its generalizability, while the latter is designed to further reduce the memory and computational overhead to enable real-time and low-latency operations. Our evaluation shows comparable performance to state-of-the-art causal inference models on synthetic data while achieving a 5x reduction of model size, 4x reduction of computation per second, 5x reduction in processing time and generalizing better to real hardware data. Further, our real-time hybrid model runs in 8 ms on mobile CPUs designed for low-power wearable devices and achieves an end-to-end latency of 17.5 ms.