• Corpus ID: 237561279

Master's Thesis: Self-Organizing Maps for Sound Corpus Organization

@inproceedings{Margraf2019MastersTS,
  title={Master's Thesis: Self-Organizing Maps for Sound Corpus Organization},
  author={Jonas Margraf},
  year={2019}
}
Large collections of audio les sound corpora have never been more readily available. Sample libraries are easily accessible online and cheap storage media e ectively eradicate concerns of storage capacity for contemporary music producers. At the same time, tools for navigating, searching and organizing these increasingly unmanageable audio le collections have not kept pace. At present, arguably the most common tool with which producers search their sample libraries are le browsers that simply… 

Towards Assisted Interactive Machine Learning: Exploring Gesture-Sound Mappings Using Reinforcement Learning

A sonic interaction design approach that makes use of deep reinforcement learning to explore many mapping possibilities between input sensor data streams and sound synthesis parameters and suggests that the implementation and evaluation of new features should take into consideration established creative workflows and take place close to actual artistic practice.

Interactive Machine Learning of Musical Gesture

This chapter presents an overview of Interactive Machine Learning techniques applied to the analysis and design of musical gestures, and outlines the implications that IML have for musical practice.

References

SHOWING 1-10 OF 61 REFERENCES

HIERARCHICAL ORGANIZATION AND VISUALIZATION OF DRUM SAMPLE LIBRARIES

This paper presents a hierarchical user interface for efficient exploration and retrieval based on a computational model of similarity and self-organizing maps for automatically structuring and visualizing large sample libraries through audio signal analysis.

SoundTorch: Quick Browsing in Large Audio Collections

User tests show that this method can leverage the human brain’s capability to single out sounds from a spatial mixture and enhance browsing in large collections of audio content.

AudioQuilt: 2D Arrangements of Audio Samples using Metric Learning and Kernelized Sorting

AudioQuilt, a system for sample exploration that allows audio clips to be sorted according to user taste, and arranged in any desired 2D formation such that similar samples are located near each other, is presented.

Mused: Navigating the Personal sample Library

An interactive scatter plot with dynamic queries to browse, discover, and select material from the personal sample library, a large database of event-synchronous audio segments extracted from a user’s digital music collection.

Meyda: an Audio Feature Extraction Library for the Web Audio API

Myda provides the first library for audio feature extraction in the web client, which will enable music information retrieval systems, complex visualisations and a wide variety of technologies and creative projects that previously were relegated to native software.

RWC Music Database: Popular, Classical and Jazz Music Databases

The design policy and specifications of the RWC Music Database are described, a music database (DB) that is available to researchers for common use and research purposes, which contains four original DBs: the Popular Music Database (100 pieces), Royalty-Free Music Database(15 pieces), Classical Music Database ($50 pieces), and Jazz Music Database (£50 pieces).

The self-organizing map

ENST-Drums: an extensive audio-visual database for drum signals processing

The aim of this paper is to present in detail the ENST-Drums database, emphasizing on both the content and the recording process, to serve research in various domains of audio signal processing involving drums.

MuBu and Friends - Assembling Tools for Content Based Real-Time Interactive Audio Processing in Max/MSP

A set of components that support a variety of different interactive real-time audio processing approaches such as beatshuffling, sound morphing, and audio musaicing are presented.

Visualizing Data using t-SNE

A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
...