Freesound technical demo

  title={Freesound technical demo},
  author={Frederic Font and Gerard Roma and Xavier Serra},
  journal={Proceedings of the 21st ACM international conference on Multimedia},
  • F. Font, Gerard Roma, X. Serra
  • Published 21 October 2013
  • Computer Science
  • Proceedings of the 21st ACM international conference on Multimedia
Freesound is an online collaborative sound database where people with diverse interests share recorded sound samples under Creative Commons licenses. It was started in 2005 and it is being maintained to support diverse research projects and as a service to the overall research and artistic community. In this demo we want to introduce Freesound to the multimedia community and show its potential as a research resource. We begin by describing some general aspects of Freesound, its architecture and… 

Figures from this paper

Generating sound palettes for a Freesound concatenative synthesizer to support creativity
This thesis focuses on the specific case of a concatenative synthesizer connected to Freesound and evaluations show that the search method does not seem to have a significant influence on the CSI score and thus on the creative process, and there is also no clear favourite in the qualitative assessment.
Improving Audio Retrieval through Loudness Profile Categorization
This paper proposes to improve search results by incorporating information about query sound's loudness profile within a thresholding based framework and can be generalized to structure information about the temporal evolution of other sound attributes.
The VU Sound Corpus: Adding More Fine-grained Annotations to the Freesound Database
A collection of annotations for a set of 2,133 environmental sounds taken from the Freesound database is presented, finding that it is not only feasible to perform crowd-labeling for a large collection of sounds, but it is also very useful to highlight different aspects of the sounds that authors may fail to mention.
SOURCE: a Freesound Community Music Sampler
  • F. Font
  • Computer Science
    Audio Mostly Conference
  • 2021
This paper describes the architecture of SOURCE and the different ways in which it interacts with Freesound and sees SOURCE as a proof of concept device that can be used as and extendable base system on top of which further research on the interaction between hardware devices and online large sound collections can be carried out.
Voice-based interface for accessible soundscape composition: composing soundscapes by vocally querying online sounds repositories
An Internet of Audio Things ecosystem devised to support soundscape composition via vocal interactions that involves a commercial voice-based interface and the cloud-based repository of audio content is presented.
Audio Commons: bringing Creative Commons audio content to the creative industries
The Audio Commons Initiative is presented, which is aimed at promoting the use of open audio content and at developing technologies with which to support the ecosystem composed by content repositories, production tools and users.
The Sound Sketchpad: Expressively Combining Large and Diverse Audio Collections
The Sound Sketchpad is proposed, an algorithm-in-the-loop audio-graphical system and interface for combining sounds from a database into new music that allows a user to sketch broad musical ideas by making sound, and then interactively modify and refine the resulting composition by drawing visual paths.
Interactive Audio Web Development Workflow
  • L. Wyse
  • Computer Science
    ACM Multimedia
  • 2014
Several areas where technologies are necessary to support the various stages of development and deployment are identified, systems developed to address those needs are described, and how they work together within a specific Web content development scenario are shown.
The Freesound Loop Dataset and Annotation Tool
The Freesound Loop Dataset (FSLD), a new large-scale dataset of music loops annotated by experts, is presented and it is anticipated that the community will find yet more uses for the data, in applications from automatic loop characterisation to algorithmic composition.
General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline
The goal of the task is to build an audio tagging system that can recognize the category of an audio clip from a subset of 41 diverse categories drawn from the AudioSet Ontology.


Freesound Radio: supporting music creation by exploration of a sound database
Comunicacio presentada al Computational Creativity Support Workshop CHI09, celebrat els dies 4 a 9 d'abril de 2009 a Boston, EUA.
Small world networks and creativity in audio clip sharing
The notion of creativity as an objective for this kind of community is proposed, and how some indicators of creativity can be extracted from user activities in these systems are proposed.
This paper analyzes the folksonomy of Freesound, an online audio clip sharing site which contains more than two million users and 150,000 user-contributed sound samples covering a wide variety of sounds, and compute some metrics that characterize the guysonomy both at the global level and at the tag level.
Characterization of the Freesound online community
This paper proposes some qualitative and quantitative approaches for the characterization of the community of sound practitioners that has emerged in Freesound, focusing on the analysis of organizational structure, shared goals, user interactions and vocabulary sharing.
Ecological Acoustics Perspective for Content-Based Retrieval of Environmental Sounds
A method to search for environmental sounds in large unstructured databases of user-submitted audio, using a general sound events taxonomy from ecological acoustics is presented.
Folksonomy-based Tag Recommendation for Online Audio Clip Sharing
This paper proposes four algorithm variants for tag recommendation based on tag co-occurrence in the Freesound folksonomy and shows how specific strategies for selecting the appropriate number of tags to be recommended can significantly improve algorithms’ performance.
Audio Metaphor: Audio Information Retrieval for Soundscape Composition
Audio Metaphor facilitated audience interaction by listening for Tweets that the audience addressed to the performance; in this case, it processed the Twitter feed in realtime to recommend audio files to the soundscape composer.
Shortest Path Techniques for Annotation and Retrieval of Environmental Sounds
This paper evaluates novel techniques for ordering query results using weights of both shortest paths and minimum cost paths of specified lengths, pruning outbound edges by nodes’ K nearest neighbors, and adjusting edge weights depending on type (acoustic, semantic, or user tagging).
Canonical dependency analysis based on squared-loss mutual information