Comprehensive processor audio benchmarking called AudioMark from EEMBC

EEMBC released audio processing benchmark called AudioMark. It is the first end to end performance benchmarking for audio processing. EEMBC claims the AudioMark is more accurate, portable and relevant compared to existing benchmarks such as speech recognition. It incorporates state-of-the-art beamforming and direction-of-arrival algorithms written by world's top Digital signal processing experts. EEMBC developed this audio benchmarking in close collaboration with embedded processing leaders Arm, Renesas, Infineon, Synopsys, onsemi, STMicroelectronics, Texas Instruments and Intel. "As digital signal processing and machine learning capabilities in modern microcontrollers advance, system designers need a benchmark that can help evaluate the AI and DSP performance of these devices," said Reinhard Keil, senior director of embedded technology, Arm. "EEMBC AudioMark is the result of close ecosystem collaboration, and addresses these requirements to provide system designers with realistic application scenarios, such as voice command control and smart speakers, as they develop innovative new products and solutions." The key features of this benchmark includes: 1. Takes both MCU and DSP processing into account considering increased reliance on DSP accelerators when designing for audio applications. 2. Uses a smaller 8-bit neural net, designed by Arm, which is ideal fo...