• Corpus ID: 53631933

Study of the signal properties of music genres

@inproceedings{Rabassedas2018StudyOT,
  title={Study of the signal properties of music genres},
  author={Andreu Boadas Rabassedas},
  year={2018}
}
The amount of music available is huge, specially if we consider free non-commercial music. In order that users can discover artists we need to design retrieval or recommendation systems which are able to organize all the available resources. Genre classification is a first step on that direction. Genre classification typically are based on supervised classification. First, the system extract classic features related to dynamic, rhythmic, spectral, and harmonic. Then a classifier (e.g. SVM) is… 

References

SHOWING 1-10 OF 21 REFERENCES
Audio Feature Engineering for Automatic Music Genre Classification
TLDR
This paper adopted a state-of-the-art machine learning algorithm, i.e. Support Vector Machines, to design an automatic classifier of music genres, and implemented some already proposed features and engineered new ones to capture aspects of songs that have been neglected in previous studies.
Music genre recognition using spectrograms
TLDR
An alternative approach for music genre classification which converts the audio signal into spectrograms and then extracts features from this visual representation and demonstrates that the classifier trained with texture compares similarly to the literature.
Evaluating Rhythmic descriptors for Musical Genre Classification
TLDR
This article considers a specific set of rhythmic descriptors for which it provides procedures of automatic extraction from audio signals and concludes on the particular relevance of the tempo and a set of 15 MFCC-like descriptors.
Combining visual and acoustic features for music genre classification
Representing Musical Genre: A State of the Art
TLDR
This article discusses the various approaches in representing musical genre, and proposes to classify these approaches in three main categories: manual, prescriptive and emergent approaches.
Factors Affecting Automatic Genre Classification: An Investigation Incorporating Non-Western Musical Forms
TLDR
Results show that various factors such as the musical features extracted, classifiers employed, the size of the dataset, excerpt length, excerpt location and test set parameters improve classification results.
Music genre recognition using spectrograms with harmonic-percussive sound separation
TLDR
This work assesses the music genre classification using spectrograms taken from the original signal, percussive content signal, and harmonic content signal to find the best rate ever obtained on the LMD dataset using artist filter constraint.
MIREX 2005 : COMBINED FLUCTUATION FEATURES FOR MUSIC GENRE CLASSIFICATION
TLDR
A system that uses combinations of three feature sets (Rhythm Patterns, Statistical Spectrum Descriptor and Rhythm Histogram) to the MIREX 2005 audio genre classification task, which achieved 75.27 % combined overall classification accuracy.
Speeding Up Music Similarity
This paper describes (1) the submission to the ISMIR’04 genre classification contest and (2) the submission to the MIREX’05 (Music Information Retrieval eXchange) audio-based genre classification and
Automatic music genre classification based on wavelet package transform and best basis algorithm
TLDR
The Top-Down search strategy with cost function to select the best basis is used and the proposed method can achieve higher classification accuracy than other music genre classification methods with the same experimental setup.
...
1
2
3
...