CSC410x - Google Project Hosting

cathamAI and Robotics

Oct 23, 2013 (3 years and 7 months ago)

175 views

A
N

APPROACH

TO

AUTOMATIC

MUSIC

PLAYLIST

GENERATION

USING

I
T
UNES

AND

BEHAVIORAL

DATA

By Darrius Serrant, Undergraduate

Supervised by Mitsunori Ogihara, PhD

CSC410: Computer Science Project Planning

A
T

A

G
LANCE


Motivation


Automatic Playlist Generation Problem


Related Work


Scope of Project


System Features


Process Overview


Testing and Evaluation


M
OTIVATION


Music: food for the soul!


Smorgasbord of expressions, emotions, and
representations


Binds us to friends, memories, experiences, etc…


Marketable, available and consumable


The typical music library


1,000+ titles


Diverse in features


Difficult to organize, explore, and experience


A
UTOMATIC

P
LAYLIST

G
ENERATION

P
ROBLEM


Manual playlist creation


Burdensome and time consuming


Subjective


Automatic playlist creation:


Create music playlists fulfilling arbitrary
requirements


# of titles


Permutation


Measure of variety


An NP
-
hard problem


R
ELATED

W
ORK


Scalable search algorithms
1


Search algorithms based on skipping behavior
2


Reduction to the traveling salesman problem
3


Local search CSP algorithm
4


Case
-
base approach to playlist generation
5


Song selection via a network flow model
6


The Music Genome Project
7



R
ELATED

W
ORK

(
CONTINUED
)


Commonalities:


Assumes limited knowledge of music library


Assumes usage of audio feature extraction techniques


Requires explicit specification of playlist constraints


S
COPE

OF

P
ROJECT


A unique approach to the automatic playlist
generation problem


Eliminates explicit user specifications


Adapts to users’ listening preferences


More expressive than audio features extraction


Research objectives


Analyze contents of users’ music library


Monitor and learn users’ listening habits


Generate playlists of twelve songs by request


S
YSTEM

F
EATURES


iTunes Library Data Extraction


Extract music titles and their characteristics


Song Characteristics Aggregator


Collect metadata from Internet sources


Machine Learning


Statistically model users’ music listening habits


Playlist Generation


Build a playlist from a “playlist” state space

S
YSTEM

F
EATURES

(
CONTINUED
)


User Feedback


Evaluation of generated playlists


Periodical mood assessments


Software application monitoring


P
ROCESS

O
VERVIEW

P
ROCESS

O
VERVIEW

1.
User listens to music through iTunes

1.
Monitor systems’ active processes

2.
Monitor local weather forecasts

3.
Receive user’s mood updates

2.
User closes down iTunes

3.
Begin pre
-
playlist generation tasks

1.
Collect data from user’s iTunes Music Library

2.
Collect data from Internet sources

3.
Update user’s listening pattern


P
ROCESS

O
VERVIEW

(
CONTINUED
)

4.
Automatically generate a new playlist

1.
Extract search heuristics from listening pattern.

2.
Build a new playlist from the search space.

5.
User evaluates the generated playlist

6.
Incorporate user feedback into listening pattern

T
ESTING

AND

E
VALUATION


Phase One: Theoretical Testing


Under simulated conditions


Tasks:


Evaluate scalability of search algorithms


Verify production of desired playlists for “naïve” users


Phase Two: Live Testing


Deliver product to actual users


Tasks:


Evaluate scalability of search algorithms for Mac and PC
users


Verify production of desired playlists for “actual” users


Test effects of volatile mood and environmental changes on
playlist generation.

C
URRENT

AND

F
UTURE

W
ORK


Version 1.0 in development


iTunes Data Extractor


Apache
Xerces

2.7 XML Parser


Data Collectors


Mood Collection


System Process Collection


Listening Pattern Assembly


Machine Learning


Weka

3.6 Supervised Learning Algorithms


Decision Tree Learning


Search Algorithms


Breadth
-
first search


Local beam search


Genetic algorithm


C
URRENT

AND

F
UTURE

W
ORK

(
CONTINUED
)


Version 1.0 in development (continued)


Data Storage


Oracle Berkeley DB Java Edition


Testing


Theoretical testing


Evaluation of developed search algorithms


Future Work


International Symposium on Music Information
Retrieval


The complete concept