Ceva Teams With Speech-Recognition Company on Optimized DSPs for CE Devices

Ceva announced at Mobile World Congress last week an optimized implementation of the iFLYTEK speech-recognition software suite for its audio and voice digital signal processors (DSP). Target products are high-volume consumer electronics, they said. The companies worked together to optimize iFLYTEK’s neural network-based speech recognition, noise reduction and echo-cancellation algorithms in the DSPs for what they said is a highly accurate, on-device voice processing solution capable of enabling multiple mics’ voice activation without requiring cloud access.