1. MACHINE LEARNING TECHNIQUES FOR MUSIC PREDICTION S. Grant Lowe Advisor: Prof. Nick Webb

2. RESEARCH QUESTIONS  Can we predict the year in which a song was released?  Can we predict the genre of a song?  Can we identify which attributes are the strongest in answering these questions?

3. BACKGROUND  Hit Song Science  Genre Classification  Year Prediction

4. APPROACH  Use WEKA  Use the Million Song Dataset

5. WEKA  Machine Learning Software  Contains Visualization tools and algorithms for data analysis and modeling

6. DATA  Million Song Data Set: commercial tracks from 1922-2011,collected by LabROSA

8. EARLY CHALLENGES  Data in the wrong Format: HDF5 vs CSV  Lots of missing Data!  Almost half of the songs are missing year, a very important attribute  Many attributes are being ignored because a majority of the songs are missing data.  ArtistID -> Year?

10. ATTRIBUTES  The MSD contains 53 descriptive attributes for each song, along with 90 timbre attributes. Attributes were removed if they were not good indicators of release year or genre, or if they were too closely tied to what was being classified.

11. ATTRIBUTE MOTIVATION  Ranked Descriptive Attributes Loudness (measured in decibels) Duration (in seconds) Tempo (estimated tempo in BPM) Time Signature (estimated beats per bar) Key Mode (major or minor)  Timbre is the quality of a musical note or sound that distinguishes different types of musical instruments, or voices. It is a complex notion also referred to as sound color, texture, or tone quality, and is derived from the shape of a segment’s spectro- temporal surface, independently of pitch and loudness.

12. EARLY RESULTS – DESCRIPTIVE ATTRIBUTES  Discretized into 6 decades; 1960-1970, 1970-1980, etc.  Baseline (Chance selection): 16.67%  First Tests: 6-9% correctly classified  More recent Tests: 25-30%  Why Random Forest and BayesNet?

13. EARLY RESULTS

14. TIMBRE RESULTS

15. GENRE PREDICTION  Genres:  Classic pop and rock  Classical  Dance and Electronica  Folk  Hip-Hop  Jazz  Metal  Pop  Rock and Indie  Soul and Reggae

16. GENRE PREDICTION RESULTS

17. CONCLUSIONS & FUTURE WORK  Timbre Attributes are better than Descriptive Attributes – Why?  Taste Profile  Lyrical/Emotional Content  Tag Dataset

18. QUESTIONS?