Share This Author
The growing hierarchical self-organizing map: exploratory analysis of high-dimensional data
The motivation was to provide a model that adapts its architecture during its unsupervised training process according to the particular requirements of the input data, and by providing a global orientation of the independently growing maps in the individual layers of the hierarchy, navigation across branches is facilitated.
The growing hierarchical self-organizing map
- M. Dittenbach, D. Merkl, A. Rauber
- Computer ScienceProceedings of the IEEE-INNS-ENNS International…
- 24 July 2000
This novel neural network model evolves into a hierarchical structure according to the requirements of the input data during an unsupervised training process and is demonstrated by organizing a real-world document collection according to their similarities.
Evaluation of Feature Extractors and Psycho-Acoustic Transformations for Music Genre Classification
From the results, both crucial and problematic parts of the algorithm for Rhythm Patterns feature extraction are identified and two new feature representations are introduced: Statistical Spectrum Descriptors and Rhythm Histogram features.
Content-based organization and visualization of music archives
With Islands of Music, a system which facilitates exploration of music libraries without requiring manual genre classification is presented, given pieces of music in raw audio format, their perceived sound similarities based on psychoacoustic models are estimated and organized on a 2-dimensional map.
Rhyme and Style Features for Musical Genre Classification by Song Lyrics
This paper presents a novel set of features developed for textual analysis of song lyrics, and combines them with and compares them to classical bag-of-words indexing approaches, and presents results for musical genre classification on a test collection in order to demonstrate the analysis.
LifeCLEF 2016: Multimedia Life Species Identification Challenges
The LifeCLEF lab proposes to evaluate 3 challenges related to multimedia information retrieval and fine-grained classification problems in 3 domains based on large volumes of real-world data and the measured challenges are defined in collaboration with biologists and environmental stakeholders to reflect realistic usage scenarios.
Improving Genre Classification by Combination of Audio and Symbolic Descriptors Using a Transcription Systems
This work transcribes audio data into a symbolic form using a transcription system, extracts symbolic descriptors from that representation and combines them with audio features to surpass the glass ceiling and improve music genre classification.
Facilitating Comprehensive Benchmarking Experiments on the Million Song Dataset
A more comprehensive set of data based on the MSD, allowing its broader use as benchmark collection, and provides a wide and growing collection of other well-known features in the MIR domain, as well as ground truth data with a set of recommended training/test splits.
Uncovering hierarchical structure in data using the growing hierarchical self-organizing map
Organizing and Exploring High-Dimensional Data with the Growing Hierarchical Self-Organizing Map
This work presents an artificial neural network model with hierarchical architecture composed of independent growing self-organizing maps to address both limitations of this model and provides a model that adapts its architecture during its unsupervised training process according to the particular requirements of the input data.