End-to-end Models with auditory attention in Multi-channel Keyword Spotting

2018/11/01 by Zhang, Haitong, Zhang, Junbo, Wang, Yujun · 1 citation
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1811.00350

Abstract

In this paper, we propose an attention-based end-to-end model for multi-channel keyword spotting (KWS), which is trained to optimize the KWS result directly. As a result, our model outperforms the baseline model with signal pre-processing techniques in both the clean and noisy testing data. We also found that multi-task learning results in a better performance when the training and testing data are similar. Transfer learning and multi-target spectral mapping can dramatically enhance the robustness to the noisy environment. At 0.1 false alarm (FA) per hour, the model with transfer learning and multi-target mapping gain an absolute 30% improvement in the wake-up rate in the noisy data with SNR about -20.

Cited by

• Multichannel Keyword Spotting for Noisy Conditions

Related

• Multichannel Keyword Spotting for Noisy Conditions
• Attention-based End-to-End Models for Small-Footprint Keyword Spotting
• End-to-End Multi-Look Keyword Spotting
• Frequency & Channel Attention Network for Small Footprint Noisy Spoken Keyword Spotting
• Sequence-to-sequence Models for Small-Footprint Keyword Spotting