2014:MIREX2014 Results

Results by Task

Train-Test Task Set

• Audio Classical Composer Identification Results   
• Audio Latin Genre Classification Results   
• Audio Music Mood Classification Results   
• Audio Mixed Popular Genre Classification Results   
• Audio KPOP Genre (Annotated by Korean Annotators) Classification Results   
• Audio KPOP Genre (Annotated by American Annotators) Classification Results   
• Audio KPOP Mood (Annotated by Korean Annotators) Classification Results   
• Audio KPOP Mood (Annotated by American Annotators) Classification Results   

Other Tasks

• Music Structure Segmentation Results
  • MIREX09 dataset  
  • RWC dataset - Quaero (MIREX10) Ground-truth  
  • RWC dataset - Original RWC Ground-truth  
  • SALAMI dataset  

• Audio Onset Detection Results  

• Audio Cover Song Identification Results

• Audio Tempo Estimation Results  
• Audio Key Detection Results  

• Audio Beat Tracking Results
  • SMC Dataset  
  • MAZ Dataset  
  • MCK Dataset  

• Audio Chord Estimation
  • MIREX ’09 Dataset  
  • Billboard ’12 Dataset  
  • Billboard ’13 Dataset  

• Audio Melody Extraction Results
  • ADC04 Dataset  
  • MIREX05 Dataset  
  • INDIAN08 Dataset  
  • MIREX09 0dB Dataset  
  • MIREX09 -5dB Dataset  
  • MIREX09 +5dB Dataset  

• Audio Tag Classification Results
  • Major Miner Tag dataset
    • Binary relevance (classification evaluation)  
    • Affinity estimation evaluation  
  • Mood Tag dataset
    • Binary relevance (classification evaluation)  
    • Affinity estimation evaluation  

• Query-by-Singing/Humming Results
  • Hidden Jang Dataset  
  • Jang Dataset  
  • ThinkIt Dataset  
  • IOACAS Dataset  
  • Subtask2 Dataset  

• Query-by-Tapping Results
  • Subtask 1, Jang dataset
  • Subtask 1, Hsiao dataset
  • Subtask 2, Jang dataset
  • Subtask 3, QBT-Extended dataset

• Audio Downbeat Estimation Results

• Real-time Audio to Score Alignment (a.k.a. Score Following) Results  

• Audio Music Similarity and Retrieval Results 
• Symbolic Melodic Similarity Results
• Singing Voice Separation 

• Multiple Fundamental Frequency Estimation & Tracking Results 

• Discovery of Repeated Themes & Sections Results