DSP Group Announces Support of TensorFlow Lite for Microcontrollers on its DBMD7 AI/ML SoC

DSP Group, Inc., a leading global provider of wireless and voice-processing chipset solutions for converged communications, announced software development kit (SDK) support for TensorFlow Lite for Microcontrollers for the DBMD7 family of low-cost, high-performance, multi-core AI and DSP processors. The SDK for the DBMD7 allows developers of AI IoT devices to cost-effectively deploy high-performance machine learning (ML) inference at the edge to avoid network latencies, minimize power consumption, ensure end-user privacy, and free up scarce network bandwidth. "DSP Group offers compelling hardware for many low-power applications, so we're excited to collaborate to offer machine learning software to help enable developers create products that wouldn't be possible otherwise," said Peter Warden, Staff Research Engineer at Google. TensorFlow Lite for Microcontrollers is an extension of TensorFlow Lite that addresses the need to run ML on memory-constrained devices with only kilobytes of memory. It comes with a specific set of optimized operations to allow the execution of ML models for applications such as wake-word detection, sound detection, and image wake-up. In addition, developers can add their own ML algorithms.