Data Augmentation for Robust Keyword Spotting under Playback Interference

TL;DR

This paper introduces a data augmentation method that improves on-device keyword spotting accuracy in noisy, real-world environments with playback interference by artificially adding background sounds during training.

Contribution

It proposes a novel data augmentation strategy that enhances keyword spotting robustness against ambient noise and residual echo in real-world scenarios.

Findings

30-45% reduction in false reject rates

Improved robustness under playback interference

Effective in real-world conditions

Abstract

Accurate on-device keyword spotting (KWS) with low false accept and false reject rate is crucial to customer experience for far-field voice control of conversational agents. It is particularly challenging to maintain low false reject rate in real world conditions where there is (a) ambient noise from external sources such as TV, household appliances, or other speech that is not directed at the device (b) imperfect cancellation of the audio playback from the device, resulting in residual echo, after being processed by the Acoustic Echo Cancellation (AEC) system. In this paper, we propose a data augmentation strategy to improve keyword spotting performance under these challenging conditions. The training set audio is artificially corrupted by mixing in music and TV/movie audio, at different signal to interference ratios. Our results show that we get around 30-45% relative reduction in false reject rates, at a range of false alarm rates, under audio playback from such devices.