Skip to content

Latest commit

 

History

History
56 lines (27 loc) · 3.65 KB

README.md

File metadata and controls

56 lines (27 loc) · 3.65 KB
Raw

Perceptual Sound Browser

alt text

Percetual Sound Browser is a demo prototype of a sound browser which enables you browsing sounds by their high-level acoustic/perceptual qualities such as brightness, roughness, hardness and depth. All these features are computed from the original audio content itself, locally. This was developed as a probe system in further investigating the scope of integrating high-level semantic features into audio production environments. In-depth qualitative expert-user studies were also conducted with industry professionals for further undestanding the needs and underlying problems in the workflow.

For the moment, this patch only uses a small customised dataset of 700 sounds (7 classes) from Freesound. But, you can integrate any freesound collections by using the attached feature extraction python scripts in the instructions.

This was developed as a part of my final thesis for Masters' in Sound and Music Computing at Music Technology Group, Barcelona. You can find a detailed explanation of the project here.

This project uses an abstraction of Freesound_Max-MSP_Modules for accessing freesound API services. (Download the repo add it in your Max 7 search patch for using it with other projects)

For timbral feature extraction,this project uses the timbral sound models developed by Andy Pearce as a part of AudioCommons initiative. And, this has been done offline using an batch extraction python script

Requirements

  • You need to have a installed version of Cycling74 Max 7 (7.3.1 atleast) in order to use the system. You can download the latest version from here

Setup

  1. Download or clone the repo to your local disk

  2. Update the api_key.json file inside the ./data folder with your freesound api credentials. In case, you don't have any, you can apply for a one at http://freesound.org/apiv2/apply/ (You need to have a registered freesound.org account in order to apply for api credentials)

  3. Open the "PerceptualSoundBrowser.maxpat" file in the home folder and enjoy browsing. In case of doubts, have a look at the following video for understanding the workflow.

Builds

For Mac OSX x64bit

You might have to install Max runtime

PS : Tested only with Mac OSX platform (Yosemite 10.10.5), should be working with other versions as well. For windows, you have to build the binary from source using Max.

Acknowledgements

Thanks to Frederic Font and Xavier Favory for their valuable suggestions.

Authors

Albin Andrew Correya

albin.a.correya@gmail.com

References

[1]. Pearce, A , Brookes, T and Mason, R. First prototype of timbral characterisation tools for semantically annotating non-musical content (2017), Audiocommons.http://www.audiocommons.org/assets/files/AC-WP5-SURREY-D5.2%20First%20prototype%20of%20timbral%20characterisation%20tools%20for%20semantically%20annotating%20non-musical%20content.pdf