From web to map exploring the world of music
Download
1 / 18

From Web to Map: Exploring the World of Music - PowerPoint PPT Presentation


  • 283 Views
  • Uploaded on

From Web to Map: Exploring the World of Music. Olga Goussevskaia Michael Kuhn Michael Lorenzi Roger Wattenhofer Web Intelligence 2008 Sydney, Australia. Music in the old da ys. Storage media Vinyl records Compact cassetts Compact discs

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'From Web to Map: Exploring the World of Music' - mike_john


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
From web to map exploring the world of music l.jpg

From Web to Map: Exploring the World of Music

Olga Goussevskaia

Michael Kuhn

Michael Lorenzi

Roger Wattenhofer

Web Intelligence 2008

Sydney, Australia


Music in the old da ys l.jpg
Music in the old days

  • 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

organization by album

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Music today l.jpg
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!

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Overview l.jpg
Overview

  • Define music similarity

  • From Perception to Web

    • Build a graph of songs

  • From Web to Map

    • Embed the graph into Euclidean space

  • Application prototype: www.musicexplorer.org

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Music similarity l.jpg
Music Similarity

Similar or different???

  • Audio content analysis

  • Metadata analysis

  • Collaborative filtering

    • “people who listen to this song also listen to that song”

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


From perception to web l.jpg
From Perception to Web

  • Data from last.fm (20M users)

    • Top-50 lists (290K lists, 1.5M distinct songs)

    • Co-occurrence analysis (normalization cosine(si,sj)=nij/(ninj)1/2)

    • 1012 (O(TB)!) pair-wise similarity values

  • Building a graph G

    • Edge weight w(si,sj) = 1/cosine(si,sj)

    • Sparsening: co-occ ≥ 2, w(si,sj) ≥ threshold

    • sim(si, sj) = length(shortestPathG(si, sj))

    • Still n = 430K, m = 6.3M, and ever growing

  • How to operate on G?

    (assuming G is sparse: m=O(n logn))

    • Shortest path computation cost: O(m+logn)=O(n logn)

    • Memory needed to retrieve one value sim(si, sj): O(m)=O(n logn)

Order of seconds on a state-of-the-art PC!

Need to store the whole G,

even if I only have 50 songs in my collection!

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


From web to map l.jpg
From Web to Map

  • Embedding: map vertices of G into points in Euclidean space, s.t. dG/dE (stretch) is “minimized”.

  • Computation cost of sim(i,j): O(1) time, O(1) memory per item

  • Embedding algorithms:

    • Multi Dimensional Scaling (MDS): O(dn2)

    • Spring embedding (Fruchterman-Reingold): O(n2 + m)

    • MIS-filtering: O(n log2 Δ)

    • High-dimensional embedding: O(nl2 + lm)

    • Landmark MDS (LMDS): O(nld + l3)

      • Adaptive computation/quality tradeoff

      • Suitable for dynamic settings

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Iterative embedding l.jpg
Iterative Embedding

  • Assumption: some links erroneously shortcut certain paths E [# random edges] = X

  • Repeat (X / f) times

    • embed G (using e.g. LMDS)

    • Remove (from G) fraction f of edges with highest stretch dE/dG

  • Example: Kleinberg graph (20x20 grid, f = 0.003)

Spring embedding

output

After 12 rounds

After 30 rounds

After 6 rounds

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Evaluation l.jpg
Evaluation

  • Music Taxonomy (www.allmusic.com)

    • Control set: 7K songs with genre information

How well does the resulting map

represent music similarity?

Genre distance

dS= LCA (least common ancestor)

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Evaluation quality measures l.jpg
Evaluation: Quality Measures

  • Distance comparison QL: average similarity increase as a function of genre distance ds

  • Embedding smoothness QR: average # of genre re-occurrences on a random line

Avg. similarity of pairs (si,sj) w/ ds(i,j)=h

Songs that belong to distant genres should be far away in the embedding.

Genre transitions in the embedding should be “smooth”.

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Evaluation iterative embedding l.jpg
Evaluation: Iterative Embedding

(430K nodes, 10 dimensions)

After 30 rounds, f=0.5%

LMDS output

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Evaluation12 l.jpg
Evaluation

Closest

neighbors

in 10D

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Applications music explorer l.jpg
Applications: Music Explorer

  • www.musicexplorer.org

    • Web service to query coordinates (current DB with 430K titles)

    • Visualization in 2D

    • Zoom level according to song popularity

    • Playlist generation based on trajectories

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Playlist generation l.jpg
Playlist generation

  • Interpolation between start and end-point

    • Smooth transition from one style to the other

    • In reality: 10 dimensions

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Music in euclidean space l.jpg
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, ...)

    • Notion of direction

coordinates are well suited for mobile applications

coordinates are well suited for

similarity based organization

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Towards a new world of music l.jpg
Towards a new world of music?

  • Euclidean representation

    • Efficient similarity computation (time and memory)

    • No server needed: distributed applications

    • Building blocks for new functionalities:

  • New scenarios:

    • Mobile file sharing

    • P2P overlay based on the map

    • Innovations at home

      • “Play anything hip-hip… not this and not closely related songs… go towards Detroit house, be there in an hour”

    • Automatic DJ (collect feedback from mobiles, generate playlists based on guests regions of interest)

Notion of Direction

(Browsing)

Volumes

(Interest Regions)

Trajectories

(Playlists)

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Conclusions l.jpg
Conclusions

  • Necessary?

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


Thanks for your attention l.jpg
Thanks for your Attention

  • Questions?

Olga Goussevskaia, ETH Zurich @ Web Intelligence 2008


ad