October 17, 2012 —
SAIL team [from left to right]: Professor Shri Narayanan, and PhD students Andreas Tsiartas, Naveen Kumar, Jangwon Kim and Ming Li.
A team of USC researchers from the Signal Analysis and Interpretation Laboratory (SAIL) of the Ming Hsieh Department of Electrical Engineering won the Interspeech 2012 Speaker Trait Challenge Award. The team was directed by Professor Shri Narayanan and led by Ph.D. students Jangwon Kim and Naveen Kumar. Other team members included Ph.D. students Andreas Tsiartas and Ming Li. This is a third such award for USC SAIL: teams from USC SAIL were winners of the Interspeech challenge awards in 2009 and 2011.
The award recognizes the best performance in a competition for automated recognition of an individual's trait from their speech patterns held as part of the 13th Annual Conference of the International Speech Communication Association held in August 2011. Interspeech is the world's largest and most comprehensive technical conference focused on speech and language processing and its applications.
SAIL’s award winning entry focused on the automatic detection of the intelligibility of pathological speech. The signal processing and pattern recognition algorithms of the competitors were tested on a database supplied by the organizers. The winning paper is entitled “Intelligibility classification of pathological speech using fusion of multiple high level descriptors." This winning approach relied on computing distinct aspects of pathological speech such as voice quality, prosody and phonotactics as well as automatically clustering similar signal behavior across individuals. The final results were from the fusion of multiple classifier subsystems. Details of this research, and other on going efforts on human centered signal processing and behavioral informatics, can be found at http://sail.usc.edu.
"Our Department congratulates Shri Nayaranan and the team of students from the Signal Analysis and Interpretation Laboratory (SAIL) for their third Interspeech 2012 Speaker Trait Challenge Award. This is an amazing record of accomplishment and continuing excellence," said EE Systems Chair Alexander A. (Sandy) Sawchuk.