On-device speech recognition software available for audio DSPs
Licensor of signal processing IP for smarter, connected devices, CEVA, has announced that an optimised implementation of iFLYTEK’s speech-recognition software suite is available for CEVA’s audio/voice DSPs. The tightly-integrated solution is available for customers and is already in production for an ultra-low power voice processor targeting high volume consumer electronics.
Speech recognition is fast becoming the Human Machine Interface (HMI) of choice for consumer electronics, the smart home, mobile and wearable devices, surveillance, automotive and IoT in general, on the back of advances in sound processing and artificial intelligence. iFLYTEK is the No.1 speech recognition solution provider in China, and a global leader in speech-based artificial intelligence technology. The companies worked together to optimise iFLYTEK’s neural network based speech recognition, noise reduction and echo-cancellation algorithms for CEVA’s advanced audio/voice DSPs. The result is a powerful and highly-accurate, on-device voice processing solution, capable of enabling multiple mics voice activation without requiring cloud access.
Ran Soffer, Vice President of marketing and corporate development at CEVA, commented: “The combination of iFLYTEK’s software and our audio/voice DSP offers a powerful solution for embedding intelligent voice applications into mass market consumer electronic devices. We look forward to expanding our relationship as the demand for on-device speech processing continues to grow rapidly.”
CEVA’s family of audio/voice/speech DSPs provide a range of solutions, from ultra-low-power always-listening smart devices, through versatile wireless audio in mobile and hearables, and up to high resolution audio processing in home entertainment and automotive. These audio/voice DSPs are suitable for developing voice-enabled solutions where power consumption and cost are critical. Having powered audio and voice in more than 6 billion devices to date, CEVA’s expertise is unrivalled in the industry. Each CEVA sound processor is supported by market-leading hardware and software development tools, software libraries and the extensive CEVAnet partner ecosystem.