as you might know we have been lately working on a tag recommendation system for Freesound. The system we’ve been working on will suggest potentially meaningful tags when you are describing your uploaded sounds or when you are editing the descriptions of already uploaded sounds. Suggested tags are displayed in a list and can be added to the sounds you’re describing.
The good news is that this system has finally been deployed in Freesound and it is ready to help you adding tags to your sounds! If you want to comment and give some feedback/ask questions about the system, please do it in this forum thread.
We hope that tag recommendation helps improving the quality and coherence of sound descriptions and eases the uploading process!
Today we need to perform some maintenance on the main Freesound internet connection starting at 10 p.m. CET (1 p.m. Pacific, 4 p.m. Eastern). You may notice that Freesound is unavailable around this time, but we will be back as soon as possible.
When you click in the “Similar sounds” button of a sound, you receive a list of sounds that are similar according to its acoustic properties. The technology that powers this feature is Essentia, a library developed during several years at the Music Technology Group of UPF, where we host and support Freesound. The descriptors computed by Essentia are also available through the Freesound API.
Essentia was recently released as an open source library, and consequently the program in Freesound that uses it is now also open source. This means that anyone can see how it works, and use this technology for open source projects (the library can also be licensed for closed source projects upon request). One interesting consequence is that you can now compute the same descriptors that Freesound uses for any sound, and, using the API, search for similar sounds from Freesound. Play a note and get sounds with the same pitch, or the same timbre, imitate sounds with your mouth… you name it, we await for your hacks!
Researchers on the Good Recording Project (University of Salford, UK) have just launched a new Web experiment investigating audio quality in Freesound samples.
The AudioBattle experiment presents participants with pairs of real samples taken from Freesound and asks them to rate which is better. The researchers hope to discover how well we can predict quality from audio features in recordings and in the metadata of sounds submitted to Freesound.
The experiment takes no more than 10 minutes and all participants are able to enter a prize draw once they finish. To take part in the experiment please visit: http://www.goodrecording.net/audiobattle/
The dares are comming back to life!
So Freesounders, I dare you to participate…
Posted in Uncategorized
Hey there freesounders!
You all know what Freesound is all about and why you like using it. However, if you want to know a bit more just watch this promotional video we’ve just released:
Share this video and help us promote Freesound and make this amazing community bigger and bigger!
On Wednesday July 10 at 11 p.m. CEST (5 p.m. Pacific, 3 p.m. Eastern) Freesound will be down for a few hours while we perform some additional maintenance on our Internet connection. We’re sorry for the inconvenience this may cause.
As part of our research towards improving Freesound we are developing a tag recommendation system to help Freesound users tagging their sounds when they are uploaded.
Before implementing the system into Freesound we have started a testing phase in which we will compare several strategies for tag recommendation that we have developed. We will choose the best recommendation system according to your input.
For this, we kindly ask you to participate in an experiment that we have set up at http://labs.freesound.org/tagrecommendation/. Please carefully read the instructions and follow all steps until the experiment is finished. It will take around 20 minutes.
Once we close the experiment we will randomly select two of the participants to receive a Freesound t-shirt as a reward!
Thank you very much in advance for your participation. We believe you’ll enjoy the experiment and will be of invaluable in helping to improve Freesound.
keep on Freesounding!
ps: you can leave comments and suggestions here
Edit: Because you can see this message it means we’re back, sooner than expected. Thank you for your patience.
On Wednesday May 29 at 1 a.m. CEST (28th 7 p.m. Pacific, 4 p.m. Eastern) Freesound will be down for a few hours while we perform some maintenance on our Internet connection. We’re sorry for the inconvenience this may cause.
Hello there Freesounders!
we would like to announce that we have introduced a couple of small new features, some of them were requested in the forums.
First of all, we have increased the number of sounds that can be described per round from 4 to 10. This will be specially useful for users that tend to upload a lot of sounds at once, and will help you have your sounds described quicker.
Also to easy up the description process, you will now be able to see the description of more than one sound at a time.
We also added query term highlighting in the sound descriptions of the search results page.
Furthermore we have added some minor layout improvements, fine-tuned anti-spam measures and updated the moderation interface in order to promote oldest sounds at the beginning of the queue. This way sound moderation will become closer to “first in first out”. And now that I’m talking about sound moderation, don’t forget that moderators are humans and do this task voluntarily in their free time. They take this responsibility very seriously and always do the moderation as fast as they can! They deserve a biiiiig hurrayyyy from the whole Freesound community!
Said that, keep on Freesounding!