T14-SoundSense

T14-SoundSense - SoundSense by Andrius Andrijauskas...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon
SoundSense by Andrius Andrijauskas
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Introduction Today’s mobile phones come with various embedded sensors such as GPS, WiFi, compass, etc. Arguably, one of the most overlooked sensors, available on every device, is the microphone. Sound captured by a mobile phone’s microphone can be a rich source of information.
Background image of page 2
Introduction From the captured sound various inferences can be made about the person carrying the phone. o Conversation detection o Activity recognition o Location classification
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Challenges Scaling Robustness Device integration
Background image of page 4
Scaling People live in different environments, containing a wide variety of everyday sounds. Typically, sounds encountered by a student will be different from those encountered by a truck driver. It is no feasible to collect every possible sound and classify it.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Robustness People carry phones in a number of different ways; for example, in the pocket, on a belt, in a bag. Location of the phone with respect to the body presents various challenges because in the same environment sound levels will vary based on the phone’s location.
Background image of page 6
Robustness Phone context alters the volume: o A – in hand of a user facing source o B – in pocket of a user facing source o C – in hand of a user facing away from
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Device Integration Algorithms that perform sound sensing must be integrated in a way not to hinder phone’s primary function. Algorithms must be simple enough to run on a mobile device. Captured audio data may be privacy sensitive, so user privacy must be protected.
Background image of page 8
SoundSense SoundSense – scalable sound sensing framework for mobile phones. It is the first general purpose sound event classification system designed specifically to address scaling, robustness, and device integration.
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Architecture
Background image of page 10
Sensing and Preprocessing Audio stream is segmented into uniform
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 12
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 40

T14-SoundSense - SoundSense by Andrius Andrijauskas...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online