iFlyTek On-Device Speech Recognition Software Now Available For CEVA's Ultra-Low Power Audio/Voice DSPs

July 3 2017, 03:00
CEVA, a leading provider of signal processing solutions for smart, connected devices, announced that an optimized implementation of iFlyTek's speech-recognition software suite is available for CEVA's audio/voice DSPs. The tightly-integrated solution is now available for developers, and the company confirmed it will start production of an ultra-low power voice processor targeting high-volume consumer electronics.

Dedicated to speech recognition applications for Human Machine Interface (HMI) in consumer electronics, the smart home, mobile and wearable devices, surveillance, automotive and IoT in general, CEVA continues to expand its range of integrated solutions available to developers and manufacturers, on the back of advances in sound processing and artificial intelligence. 

iFlyTek is the No.1 speech recognition solution provider in China, and one of the leading companies in speech-based artificial intelligence technology. CEVA worked together with iFlyTek to optimize the company's neural network based speech recognition, noise reduction and echo-cancellation algorithms for CEVA's advanced audio/voice DSPs. The result, CEVA states, is "a powerful and highly-accurate, on-device voice processing solution, capable of enabling multiple mics voice activation without requiring cloud access."

As Ran Soffer, vice president of marketing and corporate development at CEVA, confirms, "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 ideal for developing voice-enabled solutions where power consumption and cost are critical.
CEVA's “smart and connected” development platform features a 500 MHz audio-and-sensing CEVA DSP running the DSP RTOS platform, includes a multi-microphone daughter board with 13 microphones, and allows developers to measure power and optimize their DSP firmware.

CEVA partners with semiconductor companies and OEMs worldwide to create power-efficient, intelligent and connected devices for a wide range of markets, including DSP-based platforms for audio/voice/speech and ultra-low power always-on/sensing applications, as well as Bluetooth, and Wi-Fi wireless solutions. "Having powered audio and voice in more than 6 billion devices to date, CEVA's expertise is unrivaled 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," the company adds.

Established in 1999, iFlyTek is a Chinese high-tech enterprise dedicated to the research and development of intelligent speech and language technologies. iFlyTek's intelligent speech and artificial intelligence technologies such as speech synthesis, speech recognition, speech evaluation, and natural language processing, is used by more than 2,000 companies in the whole industry and holds over 70% share of the Chinese market.iFlyTek has launched its own "iFlyTek voice cloud" platform, which provides intelligent speech interaction capabilities, working with more than 80,000 project partners and more than 700 million end-users.
related items