The single-chip system advances real-time speech recognition, combining AI with reduced power use for edge device integration.
Applied Brain Research (ABR) has launched a single-chip speech recognition system. This technology is integrated into ABR’s time series processor chip, the TSP1, which supports real-time, low-latency speech recognition.
The solution incorporates the company’s innovations across several technology levels. It includes the state-space network, the Legendre Memory Unit (LMU; patented), which improves computation for time series processing. The networks are then trained and compiled using ABR’s full-stack toolchain. Finally, the network operates on ABR’s computational neural fabric, which reduces power consumption by minimizing data movement within the chip.
TSP1 is a single-chip solution for time series inference tasks such as real-time speech recognition (including keyword spotting), text-to-speech synthesis, natural language control interfaces, and sensor fusion applications. The TSP1 combines a neural processing fabric, CPU, sensor interfaces, and on-chip NVM, providing an integrated solution.
“What ABR is showcasing today has been five years in the making, starting with our earliest observations of how the brain processes memories which led to the state space network model that we derived from that study and subsequently patented,” said Dr. Chris Eliasmith, ABR’s co-founder and CTO. “From that starting point, we have innovated at every level of the technology stack to do what has never been possible for speech processing in low-powered edge devices.”
“ABR’s TSP1 is going to revolutionize how time series AI is integrated into devices at the edge,” said Kevin Conley, ABR’s CEO. “We are showcasing the fastest, most accurate self-contained speech recognition solution ever produced, with both English and Mandarin versions. The TSP1 will deliver these capabilities at 100X lower power than edge GPU solutions. And speech recognition, which we are actively engaged with customers to develop, is only the first step in commercializing the potential of this technology.”
For more information, click here.
