ED-sKWS: Early-Decision Spiking Neural Networks for Rapid,and Energy-Efficient Keyword Spotting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Zeyang, Liu, Qianhui, Yang, Qu, Peng, Yizhou, Li, Haizhou
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910493478748160
author Song, Zeyang
Liu, Qianhui
Yang, Qu
Peng, Yizhou
Li, Haizhou
author_facet Song, Zeyang
Liu, Qianhui
Yang, Qu
Peng, Yizhou
Li, Haizhou
contents Keyword Spotting (KWS) is essential in edge computing requiring rapid and energy-efficient responses. Spiking Neural Networks (SNNs) are well-suited for KWS for their efficiency and temporal capacity for speech. To further reduce the latency and energy consumption, this study introduces ED-sKWS, an SNN-based KWS model with an early-decision mechanism that can stop speech processing and output the result before the end of speech utterance. Furthermore, we introduce a Cumulative Temporal (CT) loss that can enhance prediction accuracy at both the intermediate and final timesteps. To evaluate early-decision performance, we present the SC-100 dataset including 100 speech commands with beginning and end timestamp annotation. Experiments on the Google Speech Commands v2 and our SC-100 datasets show that ED-sKWS maintains competitive accuracy with 61% timesteps and 52% energy consumption compared to SNN models without early-decision mechanism, ensuring rapid response and energy efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12726
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ED-sKWS: Early-Decision Spiking Neural Networks for Rapid,and Energy-Efficient Keyword Spotting
Song, Zeyang
Liu, Qianhui
Yang, Qu
Peng, Yizhou
Li, Haizhou
Sound
Artificial Intelligence
Audio and Speech Processing
Keyword Spotting (KWS) is essential in edge computing requiring rapid and energy-efficient responses. Spiking Neural Networks (SNNs) are well-suited for KWS for their efficiency and temporal capacity for speech. To further reduce the latency and energy consumption, this study introduces ED-sKWS, an SNN-based KWS model with an early-decision mechanism that can stop speech processing and output the result before the end of speech utterance. Furthermore, we introduce a Cumulative Temporal (CT) loss that can enhance prediction accuracy at both the intermediate and final timesteps. To evaluate early-decision performance, we present the SC-100 dataset including 100 speech commands with beginning and end timestamp annotation. Experiments on the Google Speech Commands v2 and our SC-100 datasets show that ED-sKWS maintains competitive accuracy with 61% timesteps and 52% energy consumption compared to SNN models without early-decision mechanism, ensuring rapid response and energy efficiency.
title ED-sKWS: Early-Decision Spiking Neural Networks for Rapid,and Energy-Efficient Keyword Spotting
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2406.12726