Multichannel Voice Trigger Detection Based on Transform-average-concatenate

TL;DR

This paper introduces a multichannel voice trigger detection system using a transform-average-concatenate (TAC) block that leverages all available channels, improving detection accuracy over traditional single-channel methods.

Contribution

The work proposes a novel multichannel acoustic model with a modified TAC block that utilizes all channels, enhancing voice trigger detection performance in multi-speaker scenarios.

Findings

Achieves up to 30% reduction in false rejection rate.

Effectively utilizes multichannel information for improved VT.

Demonstrates superiority over baseline channel selection methods.

Abstract

Voice triggering (VT) enables users to activate their devices by just speaking a trigger phrase. A front-end system is typically used to perform speech enhancement and/or separation, and produces multiple enhanced and/or separated signals. Since conventional VT systems take only single-channel audio as input, channel selection is performed. A drawback of this approach is that unselected channels are discarded, even if the discarded channels could contain useful information for VT. In this work, we propose multichannel acoustic models for VT, where the multichannel output from the frond-end is fed directly into a VT model. We adopt a transform-average-concatenate (TAC) block and modify the TAC block by incorporating the channel from the conventional channel selection so that the model can attend to a target speaker when multiple speakers are present. The proposed approach achieves up to 30% reduction in the false rejection rate compared to the baseline channel selection approach.