text-only page produced automatically by LIFT Text Transcoder Skip all navigation and go to page contentSkip top navigation and go to directorate navigationSkip top navigation and go to page navigation
National Science Foundation
News
design element
News
News From the Field
For the News Media
Special Reports
Research Overviews
NSF-Wide Investments
Speeches & Lectures
NSF Current Newsletter
Multimedia Gallery
Search Multimedia
Image
Video
Audio
More
Multimedia in the News
NSF Executive Staff
News Archive
 

Email this pagePrint this page
"Sound Mined" -- The Discovery Files


The Discovery Files
Audio Play Audio
The Discovery Files podcast is available through iTunes or you can add the RSS feed to your podcast receiver. You can also access the series via AudioNow® by calling 405-875-0058 on any telephone.

Audio engineers have developed a novel artificial intelligence system for understanding and indexing sound, a unique tool for both finding and matching previously un-labeled audio files.

Credit: NSF/Karson Productions

Audio Transcript:

Teaching Computers to Listen.

(Sound effect: theme music) I'm Bob Karson with the discovery files--new advances in science and engineering from the National Science Foundation.

Engineers have developed a new artificial intelligence system that could set the sound world on its ear. (Sound effect: random sounds under) It takes the tedious task of searching for sounds to a level far beyond our current capabilities. It's called "MediaMined" "mined," as in "mining for sound." It's the brainchild of engineers at Imagine Research in San Francisco.

Let's say you're the sound designer for a movie and you need a certain kind of explosion sound. (Sound effect: explosion sound) You could search sound files using the keyword, "explosion" and (Sound effect: various explosion sounds under) you'd find a lot, but your search would be limited to only files that contained your keyword. MediaMined goes much deeper, by analyzing and categorizing characteristics of the sound itself. While looking for "explosion," it might bring up files labeled "detonation," or "bomb" (Sound effect: bomb sound) because it determines the sound files contain desired qualities and it does the same thing for music searches.

The system detects the properties of the sound even musical values like timbre and pitch. Then it compares those properties to other sounds in the database and points the user to sounds it concludes are similar.

The developers see uses beyond sound in media--like a tool that measures coughing and sneezing, to help doctors diagnose and treat diseases. Now if this thing could only make coffee as well as my audio engineer.

"The discovery files" covers projects funded by the government's national science foundation. Federally sponsored research--brought to you, by you! Learn more at nsf.gov or on our podcast.

 
General Restrictions:
Images and other media in the National Science Foundation Multimedia Gallery are available for use in print and electronic material by NSF employees, members of the media, university staff, teachers and the general public. All media in the gallery are intended for personal, educational and nonprofit/non-commercial use only.

Images credited to the National Science Foundation, a federal agency, are in the public domain. The images were created by employees of the United States Government as part of their official duties or prepared by contractors as "works for hire" for NSF. You may freely use NSF-credited images and, at your discretion, credit NSF with a "Courtesy: National Science Foundation" notation. Additional information about general usage can be found in Conditions.

MP3 icon
NSF podcasts are in mp3 format for easy download to desktop and laptops, as well as mobile devices capable of playing them.

 



Email this pagePrint this page
Back to Top of page