E.Sai Satvik, Mannem Rishika, K.S.S.S. Deva Kumar, Sudersan Behera
Keywords:
keyword spotting, automatic gain control, multi-style training, small-footprint models
Abstract
We explore techniques to improve the robustness of small-footprint keyword spotting models based on deep neural networks (DNNs) in the presence of background noise and in far-field conditions. We find that system performance can be improved significantly, with relative improvements up to 75% in far-field conditions, by employing a combination of multi-style training and a proposed novel formulation of automatic gain control (AGC) that estimates the levels of both speech and background noise. Further, we find that these techniques allow us to achieve competitive performance, even when applied to DNNs with an order of magnitude fewer parameters than our baseline.
Article Details
Unique Paper ID: 162517
Publication Volume & Issue: Volume 10, Issue 10
Page(s): 317 - 323
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024