Please use this identifier to cite or link to this item: https://doi.org/10.1109/TCSI.2019.2960843
Title: Low-Energy Voice Activity Detection via Energy-Quality Scaling from Data Conversion to Machine Learning
Authors: TEO JINQ HORNG 
CHENG SHUAI 
ALIOTO,MASSIMO BRUNO 
Issue Date: 3-Jan-2020
Publisher: IEEE
Citation: TEO JINQ HORNG, CHENG SHUAI, ALIOTO,MASSIMO BRUNO (2020-01-03). Low-Energy Voice Activity Detection via Energy-Quality Scaling from Data Conversion to Machine Learning. IEEE Transactions on Circuits and Systems I: Regular Papers 67 (4) : 1378-1377. ScholarBank@NUS Repository. https://doi.org/10.1109/TCSI.2019.2960843
Rights: CC0 1.0 Universal
Abstract: In this work, voice activity detection (VAD) systems with system-level energy-quality (EQ) scaling are investigated. Compared to prior single-knob EQ scaling, multiple EQ knobs are selectively inserted into the entire signal chain from end to end. EQ knobs are dynamically co-optimized to minimize energy for a given quality target. The analysis shows that system-level EQ optimization provides several benefits and has interesting implications on the performance of machine learning-based classification, as exemplified by decision trees in this work. First, it can make quality degradation more graceful than single-knob, allowing for more aggressive energy reduction under a given quality target, while retaining the ability to operate at full quality. Also, proper system-level EQ optimization enhances fitting in machine learning-based systems (e.g., decision tree-based), suppressing both underfitting and overfitting. The analysis also shows that context-specific retraining significantly improves quality and resolves fitting issues, especially at low input SNR. Measurements on a 28nm testchip show that system-level EQ scaling can reduce energy by up to 3.5X at 2% accuracy degradation in 10-dB noise, compared to full quality. Iso-technology comparison shows that the minimum energy of 51.9 nJ/frame is lower than prior art by 1.9-74.4X at comparable speech/non-speech hit rates.
Source Title: IEEE Transactions on Circuits and Systems I: Regular Papers
URI: https://scholarbank.nus.edu.sg/handle/10635/189163
DOI: 10.1109/TCSI.2019.2960843
Rights: CC0 1.0 Universal
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LOW-EN~1.PDF948.69 kBAdobe PDF

OPEN

Post-printView/Download

SCOPUSTM   
Citations

2
checked on May 12, 2021

Page view(s)

18
checked on May 6, 2021

Download(s)

1
checked on May 6, 2021

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons