Embedded speech solution provider, Cyberon, and Andes Technology, a supplier for high efficiency, low-power 32/64-bit RISC-V processor cores, have collaborated on the edge-computing voice recognition solution, Cyberon DSpotter.
As part of the partnership, the companies will explore Andes DSP-capable RISC-V CPU cores, such as D25F and comprehensive software development environment to provide a cost-effective, high performance, and easy-to-deploy solution.
The development of AI technology has recently brought tremendous progress in speech recognition. In addition to voice assistant services based on cloud-computing architecture, there are growing demands for local voice recognition by edge-computing devices from the market. Locally executed offline command recognition provides users with a quick-response voice operation interface, protects personal privacy, and reduces the development and maintenance costs of the device manufacturers.
For many products that have a strong demand for voice control, such as wearable devices, home appliances, IoT devices, etc., low computing resource requirements and high recognition performance are important considerations. Therefore, Cyberon based on more than 20 years of professional experience, introduces its new generation algorithm, DSpotter, for voice wake-up and local command recognition.
Different from most solutions in the market, Cyberon’s DSpotter adopts phoneme-based acoustic model to improve customers’ product development efficiency. Developers do not need to collect a large amount of training corpus in advance. They can create the required commands by simply entering text. Based on the relevant foundation built over the past years, Cyberon has developed more than 40 global languages for DSpotter. It helps customers to introduce their products to the global market in a timely manner.
Regarding the recognition performance, DSpotter has high accuracy and high noise robustness due to the strength of its acoustic model consisting of TDNN-F architecture. In addition, the algorithm has been well optimised by Cyberon to fit into general MCU platforms without using a dedicated neural network processor. In this way, manufacturers can provide products with voice interfaces through cost-effective hardware.
Furthermore, the performance of DSpotter is increased significantly by leveraging RISC-V DSP/SIMD P-extension (RVP) instructions on AndesCore™ D25F, a 32-bit RISC-V CPU core with highly optimised 5-stage pipeline. The RVP enables multiple data in integer registers to be processed in one single cycle, thus efficiently boosts the computations for voice, audio, image and signal processing. It also greatly improves performance for edge AI involving the above data types. The D25F is the first market-proven RISC-V RVP-capable processor, and has the most complete ecosystem in development tools, libraries for DSP and neural networks, and audio/voice codec.
Alex Liou, VP of Cyberon Embedded solution BU, said: “The AI technology of edge computing has gradually entered people’s lives. Cyberon’s DSpotter algorithm helps developers to reduce development costs of voice recognition applications. We offer a convenient and easy-to-use tool to create customised commands of global languages. Developers can create various voice recognition applications efficiently to meet the strong and diverse demands of the market.
“The collaboration with Andes extends the application of DSpotter technology to RISC-V platforms and demonstrates excellent computing and recognition performances. It is hoped that it will bring more products with intelligent and convenient voice interface to people’s lives.”
Simon Wang, technical marketing manager of Andes Technology, and in charge of RISC-V compute acceleration ecosystem, said: ”Intelligence is now in everyone’s daily life empowering not only by cloud computing but also by edge computing. Andes offers a comprehensive 32 and 64 bit RISC-V processor core series with high computation efficiency and low power consumption for general computing solutions.
“In addition, we provide AI solutions based on RVP, RVV and ACE instruction extensions with the support of Andes NN SDK and have been cooperating with partners to extend our solutions. We are excited to work with Cyberon to offer very competitive voice recognition and voice assistant solutions for edge devices based on the strength of AndesCore D25F, esp. its RVP support.”
Want to learn more about topics like this from thought leaders in the space? Find out more about the Edge Computing Expo North America on September 29-30, a brand new, innovative event and conference exploring the edge computing ecosystem.