MobileHCI '11: Utilizing Sensor Fusion for Markerless Mobile AR
Distributed Computing Group Exploring Music Collections on Mobile Devices Michael Kuhn Olga...
-
date post
20-Dec-2015 -
Category
Documents
-
view
217 -
download
1
Transcript of Distributed Computing Group Exploring Music Collections on Mobile Devices Michael Kuhn Olga...
DistributedComputing
Group
Exploring Music Collections on Mobile Devices
Michael KuhnOlga GoussevskaiaRoger Wattenhofer
MobileHCI 2008Amsterdam, NL
2 Michael Kuhn, ETH Zurich @ MobileHCI 2008 2
• Storage media– Vinyl records– Compact cassetts– Compact discs
• An Album is stored on a single physical storage medium– Sequence of songs given by album– Album is typically listened to as a whole
History
organization by album
3 Michael Kuhn, ETH Zurich @ MobileHCI 2008 3
Music today
• Huge offer, easily available – filesharing, iTunes, amazon, etc.
• Large collections– The entire collection is stored on
a single electronic storage medium
– Organization by albums (and other lists) is no longer appropriate
organize by similarity
4 Michael Kuhn, ETH Zurich @ MobileHCI 2008 4
Contributions
• Vision– Plays songs the user likes– Overview of a collection– Directly on mp3-player (or phone)
• Problems on mobile devices– Limited input– Limited output– Limited processing power– Limited memory
• Contribution– Use song coordinates that reflect similarity– Proof-of-concept implementation on Android
5 Michael Kuhn, ETH Zurich @ MobileHCI 2008 5
Music Explorer
• www.musicexplorer.org– Webservice that provides 10D coordinates for songs– Similar songs are close to each other in Euclidean space– Similarity information based on co-occurrence data– Currently about 400K songs available
• Similarity derived by means ofco-occurrence analysis
6 Michael Kuhn, ETH Zurich @ MobileHCI 2008 6
Music in Euclidean Space
• Performance– Similarity computation comes almost for free: O(1) time– Memory footprint is extremly low: O(1) per song
– All information can be saved in the file, no server connection required.
• Applications– Trajectories (playlists, ...)– Volumes (region of interest, ...)– etc.
coordinates are well suited for mobile applications
coordinates are well suited for similarity based organization
7 Michael Kuhn, ETH Zurich @ MobileHCI 2008 7
Playlist generation
• Interpolation between start and end-point– Smooth transition from one style to the other
– In reality: 10 dimensions
8 Michael Kuhn, ETH Zurich @ MobileHCI 2008 8
Hey Jude (Beatles)
Yesterday (Beatles)
Imagine (John Lennon)
...
Massachusetts (Bee Gees)
Massachusetts (Bee Gees)
World (Bee Gees)
Odessa (Bee Gees)
...
Pet Sounds (Beach Boys)
Similarity-based Navigation• Basic idea: Browse through neighborhood lists
• Challenges– Reachability: Entire collection
should be reachable from any given starting point
– Searchability: It should be possible to reach new regions within few steps
Hey Jude (Beatles)
Yesterday (Beatles)
Imagine (John Lennon)
...
Massachusetts (Bee Gees)
Massachusetts (Bee Gees)
World (Bee Gees)
Odessa (Bee Gees)
...
Pet Sounds (Beach Boys)
d > r
r
9 Michael Kuhn, ETH Zurich @ MobileHCI 2008 9
Similarity-based Navigation (Small-World)
• J. Kleinberg: The Small-World Phenomenon: An Algorithmic Perspective, STOC’00– Augmenting a (hyper-)grid with edges following a particular length
distribution (d-r, r = #dim) leads to polylog diameter (=>reachability)
– Short paths do not only exist, but can be found using local knowledge only (=>searchability)
10 Michael Kuhn, ETH Zurich @ MobileHCI 2008 10
Similarity-based Navigation (Clustering)
• Idea: Cluster similar songs and list clusters instead of single songs– Cover entire collection (=>reachability)– Small clusters for close-by songs– Large clusters for distant regions (=>searchability)
11 Michael Kuhn, ETH Zurich @ MobileHCI 2008 11
Conclusions and Future Work
• Embedding songs into Euclidean space opens many possibilities for mobile applications
• We have presented a proof-of-concept Android application that– can create smooth playlists– allows to browse collections based on smilarity– does not require (expensive) connection to a server or DB
• Future directions– Visually browsing collections (problem: 10D => 2D)– Playlist generation on the fly– Collaborative features– ...
12 Michael Kuhn, ETH Zurich @ MobileHCI 2008 12
Thanks for your Attention
• Questions?