1 / 22

Music retrieval

Music retrieval. Conventional music retrieval systems Exact queries: ”Give me all songs from J.Lo’s latest album” What about ”Give me the music that I like”?  New methods are needed: sophisticated similarity measures Increasing importance: MP3 players (10 3 songs)

ohio
Download Presentation

Music retrieval

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Music retrieval • Conventional music retrieval systems • Exact queries: ”Give me all songs from J.Lo’s latest album” • What about ”Give me the music that I like”?  New methods are needed: sophisticated similarity measures • Increasing importance: • MP3 players (103 songs) • Personal music collections (104 songs) • Music on demand • many songs, huge market value…

  2. Proposal • Try a classifier method • Similarity measure  enables matching of fuzzy data  always returns results • Implement relevance feedback • User feedback Improves retrieval performance

  3. Classifier systems • Genetic programming • Neural networks • Curve fitting algorithms • Vector quantizers

  4. Tree structured Vector Quantization • Audio parameterization Feature space: MFCC coefficients • Quantization tree A supervised learning algorithm, TreeQ: • Attempts to partition feature space for maximum class separation

  5. Features: MFCC coefficients waveform 100 Hamming windows/second DFT Log Mel IDFT MFCCs: A 13-dimensional vector per window 5 minutes song  30103 windows

  6. Classifying feature space

  7. Nearest neighbor Discrimination line in feature space • Problems: • Curse of dimensionality • Distribution assumptions • Complicated distributions

  8. Each surface is added such that It cuts only one dimension (speed) the mutual information is maximized: Vector Quantization:Adding decision surfaces

  9. Until further splits are not worthwile – according to certain stop conditions

  10. Decision tree • Tree partitions features space • L regions (cells/leaves) • Based on class belonging of training data

  11. Template generation • Generate templates for • Training data • Test data • Each MFCC vector is routed through the tree

  12. Template generation • With a series of feature vectors, each vector will end up in one of the leaves. • This results in a histogram, or template, for each series of feature vectors.

  13. Augmented similarity measure, e.g. DiffSim(X) = sim(X,A) –sim(X,C) Template comparison Corpus templates – one per training class A B n Query template Compute similarity X sim(X,A), sim(X,B), sim(X,C), …sim(X,n)

  14. Result list Template comparison Corpus templates – one per training class A B n Query templates Compute similarity DiffSim(X) Sort

  15. Preliminary experiments • Test subjects listened to 107 songs Rated them: good, fair, poor (class belonging Cg, Cf, Cp) • Training process: • For each user • Select randomly a subset (N songs) from each class • Construct a tree based on class belonging • Generate histogram templates for Cg, Cf, Cp • For each song X • Generate histogram template • Compute DiffSim(X) = sim(X,Cg) – sim(X,Cp) • Sort the list of songs according to DiffSim

  16. Results

  17. Result list Relevance feedback classifier user

  18. Implementation Adjust histogram profiles based on user feedback • For each user • Select the top M songs from the result list • Add the contents of the songs to the histogram profile based on the user rating (class belonging Cg, Cf, Cp) • For each song X • Generate histogram template • Compute DiffSim(X) = sim(X,Cg) – sim(X,Cp) • Sort the list of songs according to DiffSim

  19. Improvement

More Related