att_abstract={Smartphones are excellent mobile sensing platforms, with the microphone in particular being exercised in several audio inference applications. We take smartphone audio inference a step further and demonstrate for the first time that it’s possible to accurately estimate the number of people talking in a certain place - with an average error distance of 1.5 speakers - through unsupervised machine learning analysis on audio segments captured by the smartphones. Inference occurs transparently to the user and no human intervention is needed to derive the classification model. Our results are based on the design, implementation, and evaluation of a system called Crowd++, involving 120 participants in 6 very different environments. We show that no dedicated external hardware or cumbersome supervised learning approaches are needed but only off-the-shelf smartphones used in a transparent manner. We believe our findings have profound implications in many research fields, including social sensing and personal wellbeing assessment.},
	att_authors={yc2591, em269d},
	att_copyright_notice={(c) ACM, 2013. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in 2013 {{, 2013-09-08}}{{, http://delivery.acm.org/10.1145/2500000/2493435/p43-xu.pdf?ip=}}.
	att_tags={Audio sensing,  Smartphone Sensing,  Multi-speaker,  Classification,  Clustering},
	author={Xu, Chenren and Li, Sugang and Liu, Gang and Zhang, Yanyong and Miluzzo, Emiliano and Chen, Yih-Farn and Li, Jun and Firner, Bernhard},
	booktitle={Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing},
	institution={{UbiComp 2013}},
	title={Crowd++: unsupervised speaker count with smartphones},