Researchers at the University of Texas at Dallas are developing speech-processing technology to transcribe thousands of hours of audio conversations between astronauts, mission-control specialists, and back-room support staff during the Apollo moon missions.
The researchers had to digitize more than 200 reels of obsolete analog tapes using a decades-old device that only reads one track at a time, and the team created a 30-track read head that cut the digitizing process down to a matter of months, and also developed software to process the speech. In addition, the researchers developed algorithms that distinguish different voices on the recordings and generate a timeline of who is speaking when and with whom. The team also built a predictive lexicon for the speech-recognition software.
The researchers say they used the tools to process all 19,000 hours of Apollo audio, which the U.S. National Aeronautics and Space Administration will soon release to the public.
From Government Computer News
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found