Speech activity detection using accelerometer
- 1 August 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2012 (1094687X) , 2112-2115
Abstract
The level of social activity is linked to the overall wellbeing and to various disorders, including stress. In this regard, a myriad of automatic solutions for monitoring social interactions have been proposed, usually including audio data analysis. Such approaches often face legal and ethical issues and they may also raise privacy concerns in monitored subjects thus affecting their natural behaviour. In this paper we present an accelerometer-based speech detection which does not require capturing sensitive data while being an easily applicable and a cost-effective solution.Keywords
This publication has 13 references indexed in Scilit:
- Inferring colocation and conversation networks from privacy-sensitive audio with implications for computational social scienceACM Transactions on Intelligent Systems and Technology, 2011
- BeWell: A Smartphone Application to Monitor, Model and Promote Wellbeing2011
- Augmentative Communication Based on Realtime Vocal Cord Vibration DetectionIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2010
- Exploiting Nonacoustic Sensors for Speech EncodingIEEE Transactions on Audio, Speech, and Language Processing, 2006
- Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movementPhysiological Measurement, 2004
- Cross-modal prediction in audio-visual communication2002
- Physiologic and acoustic differences between male and female voicesThe Journal of the Acoustical Society of America, 1989
- Social Relationships and HealthScience, 1988
- Chest Wall Vibrations in SingersJournal of Speech, Language, and Hearing Research, 1983
- Adaptive noise cancelling: Principles and applicationsProceedings of the IEEE, 1975