Aggregate features and ADABOOST for music classification
By James Bergstra, Norman Casagrande, Dumitru Erhan, Douglas Eck, Balázs Kégl. Machine-mediated learning, 2006
328 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
View Paper: https://www.semanticscholar.org/paper/1d1936a3488d1fde6ef03c124a798c30c6cb7d9c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Yoshua Bengio
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Ming-Hsuan Yang
- Jitendra Malik
- Andrew Zisserman
In Signal Processing
- Yoshua Bengio
- Emmanouil Benetos
- Pascal Vincent
- Simon E. Dixon
- Siddharth Sigtia
- Douglas Eck
- Nicolas Boulanger-Lewandowski
- Philippe Hamel
Citations in the corpus
- Applied Predictive Modeling (2013, background): “2003), and music genre identification (Bergstra et al. 2006), to name a few.”
- Analysis of Machine Learning Techniques for Heart Failure Readmissions (2016, methodology): “Boosting algorithms harness the power of weaker predictors by creating combined and weighted predictive variables.(18,19) This technique has been applied to preliminary learning work with electronic health records.”
- A Survey of Audio-Based Music Classification and Annotation (2011, methodology): “Other low-level features are also used in combination with MFCC in many systems to further improve the performance, such as STFT [1] , [12] , [9], [84], OSC [18], [123], ASE [18], [123], and DWCH [12].”
- Are the Emotions Expressed in Music Genre-specific? An Audio-based Evaluation of Datasets Spanning Classical, Film, Pop and Mixed Genres (2011, background): “Interestingly, no systematic studies have yet been conducted to assess the relative genre-specificity of musical features that communicate certain emotions, even though it seems intuitive that genre should play a major role in determining what those features might be, particularly since the high suc”
- Learning Features from Music Audio with Deep Belief Networks (2010, methodology): “With the aggregation, our classification accuracy by jumped to 84.3%, which is better than the 83% accuracy reported in [4].”
- Audio Chord Recognition with Recurrent Neural Networks (2013, methodology): “A popular enhancement that we also employ consists in the use of multiscale aggregated features to describe context information [4, 10, 14].”
- An End-to-End Neural Network for Polyphonic Piano Music Transcription (2015, background): “over several frames of inputs [26], [33], [34].”