DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning

Advanced search
Browse by:

Department | Year

UCL Theses | Latest

Deposit your research

DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning

Lane, ND; Georgiev, P; Qendro, L; (2015) DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning. In: Miyahara, H and Tokuda, H and Mase, K and Langheinrich, M, (eds.) Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. (pp. pp. 283-294). Association for Computing Machinery: Osaka, Japan. Green open access

[thumbnail of Lane, Georgiev, & Qendro 2015 UbiComp.pdf]

Preview

Text
Lane, Georgiev, & Qendro 2015 UbiComp.pdf - Published Version
Download (8MB) | Preview

Abstract

Microphones are remarkably powerful sensors of human behavior and context. However, audio sensing is highly susceptible to wild fluctuations in accuracy when used in diverse acoustic environments (such as, bedrooms, vehicles, or cafes), that users encounter on a daily basis. Towards addressing this challenge, we turn to the field of deep learning; an area of machine learning that has radically changed related audio modeling domains like speech recognition. In this paper, we present DeepEar - the first mobile audio sensing framework built from coupled Deep Neural Networks (DNNs) that simultaneously perform common audio sensing tasks. We train DeepEar with a large-scale dataset including unlabeled data from 168 place visits. The resulting learned model, involving 2.3M parameters, enables DeepEar to significantly increase inference robustness to background noise beyond conventional approaches present in mobile devices. Finally, we show DeepEar is feasible for smartphones by building a cloud-free DSP-based prototype that runs continuously, using only 6% of the smartphone's battery daily.

Type:	Proceedings paper
Title:	DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning
Event:	UbiComp '15 ACM International Joint Conference on Pervasive and Ubiquitous Computing - September 07 - 11, 2015
ISBN-13:	9781450335744
Open access status:	An open access version is available from UCL Discovery
DOI:	10.1145/2750858.2804262
Publisher version:	http://dx.doi.org/10.1145/2750858.2804262
Language:	English
Additional information:	This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. © 2015 ACM
Keywords:	Mobile sensing, deep learning, audio sensing.
UCL classification:	UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI:	https://discovery.ucl.ac.uk/id/eprint/1503675