Home / News / Mary Harper: IARPA Wants Speech Recognition Tech for Reverberant Environments

Mary Harper: IARPA Wants Speech Recognition Tech for Reverberant Environments

IARPA_logo_EMThe Intelligence Advanced Research Projects Activity aims to find speech recognition software for deciphering conversations in noisy areas through a $50,000 prize challenge.

IARPA’s Automatic Speech Recognition in Reverberant Environments challenge will give participants access to sample microphone data for ASR platform testing, the agency said Tuesday.

“Building speech recognition systems that work well on speech recorded in mismatched noisy, reverberant environments is essential for many intelligence community missions,” said Mary Harper, a program manager at IARPA.

“Speech recognition technology performs best when the data used to train a system matches the data used to evaluate it,” Harper added.

Evaluation of single-microphone ASpIRE systems will run from Feb. 4-11, 2015, with assessment for multimicrophone platforms to be held the following week.

The agency will award $30,000 and $20,000 to the winning participants in the single microphone and multimicrophone categories, respectively.

Check Also

DARPA Launches Program Seeking High Performance Computing for Military Simulators

The Defense Advanced Research Projects Agency launched a new program to improve how virtual training environments replicate real-world interactions and host more complex systems. DARPA unveiled Monday that the Digital RF Battlespace Emulator program intends to build a new breed of High Performance Computing capable of supporting advanced radio frequency for simulators. 

Leave a Reply

Your email address will not be published. Required fields are marked *