University of Jaen (UJA) telecommunications engineers have developed a method to automatically detect and identify musical notes in an audio file and generate sheet music. The system can identify notes from different instruments, musicians, types of music, or recording studio conditions. “We propose an automatic system to detect and transcribe musical notes for one-instrument musical signals which, unlike other methods, is capable of adapting to the music scene,” says UJA’s Julio Jose Carabias. “Automatic music transcription has many practical applications for musicological analysis and is of enormous assistance, for example, in recovering musical content, separating audio sources, and codifying or converting audio files.” The researchers’ method converts WAV music files into MIDI files, which makes it possible to visualize the sheet music and listen to the result. “Another advantage of this method is that it does not require prior training with a musical database,” Carabias says.
View Full Article
For More Information Visit: http://www.cpccci.com

Vienna University of Technology researchers have developed the “deanonymization” attack as a way to reveal the identity of Internet users based on their interactions in social networks. The attack uses social networking groups as well as traditional browser history-stealing tactics to single out specific users. The researchers focused on Germany’s Xing business social network and Facebook and matched stolen browsing histories with social network group members to identify users. “It is the combination of history stealing and group information that is novel,” says Vienna University post-doctoral researcher Gilbert Wondracek. Criminals could use the deanonymization method for targeted attacks, which only requires that the victim visit a malicious Web site that contains the attack code. There is no fix for the attack, but users can turn off their browsing history or use a private-browsing mode to minimize the risk.
View Full Article
For More Information Visit: http://www.cpccci.com

Japanese scientists have developed a statistical program that could enable portable baby-monitoring devices to determine whether infant cries mean a baby is sleepy, hungry, needs a change, or is in pain. Tomomasa Nagashima and colleagues at the Muroran Institute of Technology used a sound pattern recognition strategy to analyze infants’ crying patterns. The team analyzed the frequency of cries and the power function of the audio spectrum to classify different types of crying. Nagashima and colleagues were able to correlate the different recorded audio spectra with the emotional state of a baby as confirmed by the parents. Recordings of a crying baby with a painful genetic disorder helped the researchers differentiate the cries of babies who are in pain. They were able to achieve a 100 percent success rate in classifying pained cries and normal cries via their technique.
View Full Article
For More Information Visit: http://www.cpccci.com