DSP Group Unveils DBM10 Low-Power Edge AI/ML SoC with Dedicated Neural Network Inference Processor
January 07 2021 - 7:00AM
DSP Group,
Inc. (NASDAQ:
DSPG), a leading global provider of wireless and
voice-processing chipset solutions for converged communications
today announced the DBM10, a low-power, cost-effective artificial
intelligence (AI) and machine learning (ML) system on chip (SoC).
The SoC comprises a digital signal processor (DSP) and the
company’s nNetLite neural network (NN) processor, both optimized
for low-power voice and sensor processing in battery operated
devices. This architecture offers developers full flexibility of
partitioning innovative algorithms between DSP and NN processor and
enables fast TTM for integration of voice and sensing algorithms
such as noise reduction, AEC, wake-word detection, voice activity
detection and other ML models. The DBM10 features an open platform
approach with a comprehensive software framework. This allows
developers to quickly get next-generation designs to market with
their own algorithms, or with DSP Group’s comprehensive and proven
suite of optimized algorithms for voice, sound event detection
(SED), and sensor fusion for applications ranging from true
wireless stereo (TWS) headsets to smartphones, tablets, wearables,
and IoT.
“Edge applications for AI are many and diverse,
but almost all require the ultimate in terms of low power, small
form factor, cost effectiveness, and fast time-to-market, so we are
very excited about what the DBM10 brings to current and new
customers and partners,” said Ofer Elyakim, CEO of DSP Group. “Our
team has worked to make the absolute best use of available
processing power and memory for low-power AI and ML at the
edge—including developing our own patent-pending weight compression
scheme—while also emphasizing ease of deployment. We look forward
to seeing how creatively developers apply the DBM10 platform.”
“SoCs with the appropriate processors for
critical functions are key to enabling innovative products with
acceptable battery life,” said Phil Solis, Research Director at
IDC. “Such SoCs, with audio and sound DSPs and NPUs, need to
support common frameworks and standards to enable competitive
voice- and other sound-enabled smart products across end-user and
IoT devices.”
The DBM10 adds to DSP Group’s SmartVoice line of
SoCs and algorithms that are deployed globally in devices ranging
from smartphones and laptops/PCs, to set-top boxes, tablets, remote
controls, and smart IoT devices for the home. SmartVoice last year
reached the 100 million units shipped milestone, so the low-power
DBM10 is supported by an established ecosystem of third-party
algorithm providers. Key partners have integrated already their NN
algorithms on the nNetLite NN processor at the heart of the DBM10
to achieve maximum performance at the lowest power consumption.
Working alongside a programmable low-power DSP,
the nNetLite processor supports all standard deep NN (DNN) and ML
frameworks and employs a comprehensive cross-platform toolchain for
model migration and optimization.
Key specifications include:
- A highly-compact form factor: ~4
mm2
- Ultra-low-power inference
consume~500 µW for voice NN algorithms
- Runs Hello Edge 30-word detection
model @ 1 MHz (125 MHz available)
- Allows porting of large models (10s
of megabytes) without significant accuracy loss using model
optimization and compression.
About DSP GroupDSP Group®, Inc.
(NASDAQ: DSPG) is a global leader in wireless communications and
voice processing chipsets and algorithms for a wide range of
smart-enabled devices. The company was founded in 1987 on the
principles of experience, insight, and continuous advancement. We
seek to consistently deliver next-generation solutions in the areas
of voice, audio, video, and data connectivity. Building upon our
core competencies in the area of voice processing, DSP Group
invests heavily in innovation for the smart future. The result is
leading-edge semiconductor and product development technology that
allows our customers to develop products that enhance the end-user
experience. From AI-enabled TWS headsets to the voice-enabled smart
home. From IoT, security, mobile handsets, tablets, and laptops,
all the way to full enterprise-level unified communications (UC)
across cloud-based voice services, DSP Group applies its core
engineering and technical support capabilities to help its
customers meet the demands of an ever-expanding universe of
voice-enabled, connected, smart devices. Visit us at www.dspg.com
or follow us on LinkedIn and Twitter, as well YouTube, where you
can see our solutions in action.
Contact:Shiri Weiss Ovadia
Marketing & Communications DSP Group Inc.+1 (408)
986-4300Shiri.Weiss@dspg.com
DSP (NASDAQ:DSPG)
Historical Stock Chart
From Mar 2024 to Apr 2024
DSP (NASDAQ:DSPG)
Historical Stock Chart
From Apr 2023 to Apr 2024