eprintid: 1503675 rev_number: 30 eprint_status: archive userid: 608 dir: disk0/01/50/36/75 datestamp: 2017-05-30 12:22:06 lastmod: 2021-10-10 22:52:31 status_changed: 2017-05-30 12:22:06 type: proceedings_section metadata_visibility: show creators_name: Lane, ND creators_name: Georgiev, P creators_name: Qendro, L title: DeepEar: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments using Deep Learning ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Mobile sensing, deep learning, audio sensing. note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. © 2015 ACM 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. date: 2015-09-11 date_type: published publisher: Association for Computing Machinery official_url: http://dx.doi.org/10.1145/2750858.2804262 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1122803 doi: 10.1145/2750858.2804262 isbn_13: 9781450335744 lyricists_name: Lane, Nicholas lyricists_id: NLANE01 actors_name: Lane, Nicholas actors_id: NLANE01 actors_role: owner full_text_status: public series: ACM International Joint Conference on Pervasive and Ubiquitous Computing publication: UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing volume: 2015 place_of_pub: Osaka, Japan pagerange: 283-294 event_title: UbiComp '15 ACM International Joint Conference on Pervasive and Ubiquitous Computing - September 07 - 11, 2015 book_title: Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing editors_name: Miyahara, H editors_name: Tokuda, H editors_name: Mase, K editors_name: Langheinrich, M citation: 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 document_url: https://discovery.ucl.ac.uk/id/eprint/1503675/1/Lane%2C%20Georgiev%2C%20%26%20Qendro%202015%20UbiComp.pdf