Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder

by   Alexandre Bittar, et al.

Using a vision-inspired keyword spotting framework, we propose an architecture with input-dependent dynamic depth capable of processing streaming audio. Specifically, we extend a conformer encoder with trainable binary gates that allow us to dynamically skip network modules according to the input audio. Our approach improves detection and localization accuracy on continuous speech using Librispeech top-1000 most frequent words while maintaining a small memory footprint. The inclusion of gates also reduces the average amount of processing without affecting the overall performance. These benefits are shown to be even more pronounced using the Google speech commands dataset placed over background noise where up to 97 therefore making our method particularly interesting for an always-on keyword spotter.


page 1

page 2

page 3

page 4


Encoder-Decoder Neural Architecture Optimization for Keyword Spotting

Keyword spotting aims to identify specific keyword audio utterances. In ...

DCCRN-KWS: an audio bias based model for noise robust small-footprint keyword spotting

Real-world complex acoustic environments especially the ones with a low ...

Small Footprint Multi-channel ConvMixer for Keyword Spotting with Centroid Based Awareness

It is critical for a keyword spotting model to have a small footprint as...

To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement

Keyword spotting systems continuously process audio streams to detect ke...

Small-footprint slimmable networks for keyword spotting

In this work, we present Slimmable Neural Networks applied to the proble...

EfficientNet-Absolute Zero for Continuous Speech Keyword Spotting

Keyword spotting is a process of finding some specific words or phrases ...

SpeechYOLO: Detection and Localization of Speech Objects

In this paper, we propose to apply object detection methods from the vis...

Please sign up or login with your details

Forgot password? Click here to reset