https://www.iotworldtoday.com/wp-content/themes/ioti_child/assets/images/logo/mobile-logo.png
  • Home
  • News
    • Back
    • Roundups
  • Strategy
  • Special Reports
  • Business Resources
    • Back
    • Webinars
    • White Papers
    • Industry Perspectives
    • Featured Vendors
  • Other Content
    • Back
    • Q&As
    • Case Studies
    • Features
    • How-to
    • Opinion
    • Podcasts
    • Strategic Partners
    • Latest videos
  • More
    • Back
    • About Us
    • Contact
    • Advertise
    • Editorial Submissions
  • Events
    • Back
    • Embedded IoT World (Part of DesignCon) 2022
Iot World Today
  • NEWSLETTER
  • Home
  • News
    • Back
    • Roundups
  • Strategy
  • Special Reports
  • Business Resources
    • Back
    • Webinars
    • White Papers
    • Industry Perspectives
    • Featured Vendors
  • Other Content
    • Back
    • Q&As
    • Case Studies
    • Features
    • How-to
    • Opinion
    • Podcasts
    • Strategic Partners
    • Latest videos
  • More
    • Back
    • About Us
    • Contact
    • Advertise
    • Editorial Submissions
  • Events
    • Back
    • Embedded IoT World (Part of DesignCon) 2022
  • newsletter
  • IIoT
  • Cities
  • Energy
  • Homes/Buildings
  • Transportation/Logistics
  • Connected Health Care
  • Retail
  • AI
  • Metaverse
  • Development
  • Security
ioti.com

Embedded Computing


Google

‘Edge NLP’ Is About Doing More With Less

Digital assistants, enabled by natural language processing can execute a range of functions. But 'edge NLP,' has little use when embedded in devices with limited resources and connectivity.
  • Written by Peter Bartolik
  • 19th January 2021

The ease with which we use digital assistants such as Apple’s Siri and Amazon’s Alexa illustrates the potential of natural language processing (NLP) to create better human-to-computer interfaces. But the computers, smartphones and smart speakers on which we access those assistants exploit powerful processors, generous memory, and, generally, cloud connectivity that may not be available to many edge devices. As a result, scientists and developers are striving for more resource-efficient ways to process the spoken and written word.

Most humans communicate primarily through speech and text, and efforts to convert that through NLP date back to the 1940s. Turing’s seminal 1950 paper on testing what we now call artificial intelligence (AI) was founded in large part on whether humans could converse textually with a computer without realizing it is a machine. And in 1954, an IBM computer “within a few seconds” translated more than 60 Russian sentences “into easily readable English.”

By 2011, IBM’s Watson demonstrated its ability “to understand the actual meaning behind words, distinguish between relevant and irrelevant content, and ultimately demonstrate confidence to deliver precise final answers” by competing against humans in the “Jeopardy” quiz show.

Advances in machine learning, speech recognition technology, and access to ever-larger compute resources have progressed NLP to the point where in 2020 an estimated 128 million people in the U.S. used a voice assistant at least monthly and Google claimed a half billion users worldwide for its Google Assistant.

 

<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<>>mil>>>>

For more on AI, check out our AI in IoT conference. Register here.

>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>

Connectivity Vs. Cost and Latency

Whether accessed by voice or text command, digital assistants can execute a range of functions, from dialing a call to roaming through online databases to extract needed information. But these assistants have little use when embedded in edge devices with limited resources and connectivity. embedded devices aren’t encumbered by the latency of cloud processing, and developers don’t have to bear the costs of running cloud instances or paying for cloud-based speech recognition services.

Kadho, developer of the KidSense.ai engine for children’s automatic speech recognition in multiple languages, asserted that “speech recognition API [application programing interface] calls usually cost from $4 for 1,000 API calls or approximately $.024 per minute of audio input.” The company was subsequently acquired in early 2020 by ROYBI and incorporated into the ROYBI Robot AI-powered smart learning tool.

The KidSense Edge offline automatic speech recognition capability and provides accuracy and little latency. Addressing the challenges and tradeoffs of embedded NLP, ROYBI CTO Ron Cheng said via an email dialogue that “The most challenging is the computing capacity and power consumption.”

Because the product is portable, it requires a low-power consumption chip to continuously enable voice and face recognition. In addition, the Smart AI engine can narrow down the dictionary automatically based on a child’s selection of specified topics and lessons, reducing the need for local compute and storage.

“There’s definitely incentive to do more locally,” said Dan Miller, lead analyst and founder of Opus Research, which focuses on the merging of intelligent assistant technologies, conversational intelligence, intelligent authentication, enterprise collaboration and digital commerce.  “We’ve overcome a lot of the old challenges in just pure speech recognition, so you can get accurate recognition and you can get some human, less robotic responses, and you can do it locally.”

Jumpstarting NLP at the Edge

Companies such as Sensory and Expert.ai are providing developers with free tools to jumpstart efforts to create edge NLP applications. “The typical challenges in the embedded environment are memory size; processor load; and speed; and those are the dials that you turn to create an optimal user experience in an embedded platform,” said Joe Murphy, a vice president with Sensory, a pioneer of neural network approaches for embedded speech recognition in consumer electronics that was founded in 1994.

Companies in the consumer electronics market are trying to squeeze in more and more embedded AI features with fewer and fewer resources, he said, adding, “Doing more with less is basically what AI on the edge is tasked with.” One way to enable more features is to use specialized neural network accelerators for embedded devices.

“Many people assume there’ll be less accuracy with a speech recognition model that is embedded on a device versus one that is in the cloud, but in our experience that’s not the case,” said Sensory’s Murphy. “We create what we’ll call a specialist or a domain-specific assistant.” He contrasted that specialized, embedded NLP model to a cloud-based generalist assistant that lacks domain-specific context to understand a series of related commands such as “Start cooking” and “Stop.”

Fine-Tuning Models

Developers have also become more efficient at developing edge NLP models and fine-tuning them for specific needs. Sensory, for example, is able to build voice NLP models based on computer-generated data and to reduce reliance on the more time-consuming and costly process of physically recording numbers of people speaking words and phrases in different dialects and languages.

NLP relies on large corpuses of data that enable deep learning neural networks and can be “gargantuan” said Alexander Wong, the Canada Research Chair in Artificial Intelligence and Medical Imaging and an associate professor in the Department of Systems Design Engineering at the University of Waterloo, as well as co-founder of DarwinAI. He and other researchers “have been looking at ways to greatly reduce the complexity of such deep neural networks so that you can actually have everything running on the edge locally on your device.”

NLP has already made great strides in sifting through large volumes of text to understand the overall structure of the data, interpret it and even infer human intent or emotion. Speech adds additional compute complexity as, according to Wong, algorithms first have to decompose a graphical representation of sound waves to understand what a person is saying and reconstruct a text that can be interpreted.

It may be a while before edge NLP to progress, where devices can engage in conversation with humans that lives up to the Turing Test, but Wong said it would be a mistake for developers and businesses to take a wait-and-see posture.

“We’re making huge progress,” he said. “The industries that see the most impact, of course, are consumer electronics and big tech, but it’s to the point where a lot of different industries from healthcare to manufacturing to automotive are paying serious attention.”

With NLP, like almost every other technology these days, the pace of change has accelerated. Applying this to the edge is guiding science and businesses in more efficient and cost-effective directions to a point where NLP can readily pull meaning out of the dialogue between human and machine and react accordingly in real time.

 

 

 

 

 

 

 

 

Tags: Artificial intelligence/machine learning Embedded Computing Technologies

Related


  • IoT and Drones Automate Field Operations
    IoT-enabled drone technology has brought cost and operational efficiency to various industries.
  • Training and Development on the Mechanism of Metal Gears. in the design of information related to business
    Using Low-Code and No-Code in IoT App Development
    Developing applications for the Internet of Things is no easy feat. Connected things typically involve the integration of a disparate mix of technologies, including back-end systems, IoT endpoints, other platform and data sources. Additionally, companies that aim to build Internet of Things( IoT) applications need developers with specialized skills that allow them to configure and […]
  • Semiconductor Industry Growth Spikes, But Supply Remains Constrained
    Demand for semiconductors is white-hot as remote work and the appetite for consumer electronics continue unabated. But supply chain dysfunction could threaten semiconductor industry growth.
  • IoT security
    IoT Device Security at the Edge Poses Unique Challenges
    IoT device security at the edge is running up against the limits of traditional data center methods to secure edge devices.

Leave a comment Cancel reply

-or-

Log in with your IoT World Today account

Alternatively, post a comment by completing the form below:

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Content

  • How to Run Docker on IoT Devices
  • Jetting to the Stars Using Containers for Development
  • Network Connectivity Paves Way, with Caveats, for IoT Adoption
  • 5G in Manufacturing Shows Promise, but Rollouts Are Incremental

Roundups

View all

IoT Product Roundup: PTC, Nokia, Arm and More

19th May 2022

IoT Deals, Partnerships Roundup: Intel, Nauto, Helium and more

14th May 2022

IoT Product Roundup: Amazon, Synaptics, Urban Control and More

27th April 2022

White Papers

View all

The Role of Manufacturing Technology in Continuous Improvement Ebook

6th April 2022

IIoT Platform Trends for Manufacturing in 2022

6th April 2022

Latest Videos

View all
Dylan Kennedy of EMQ

Embedded IoT World 2022: Dylan Kennedy of EMQ

Dylan Kennedy, EMQ’s VP of global operations, sat down with Chuck Martin at Embedded IoT World 2022.

Embedded IoT World 2022: Omdia’s Sang Oh Talks Vehicle Chip Shortage

Omdia’s automotive semiconductor analyst sits down with Chuck Martin at this year’s event

E-books

View all

How Remote Access Helps Enterprises Improve IT Service and Employee Satisfaction

12th January 2022

An Integrated Approach to IoT Security

6th November 2020

Webinars

View all

Rethinking the Database in the IoT Era

18th May 2022

Jumpstarting Industrial IoT solutions with an edge data management platform

12th May 2022

AI led Digital Transformation of Manufacturing: Time is NOW

9th December 2021

Special Reports

View all

Omdia’s Smart Home Market Dynamics Report

7th January 2022

Cybersecurity Protection Increasingly Depends on Machine Learning

28th October 2020

IoT Security Best Practices for Industry and Enterprise

20th October 2020

Twitter

IoTWorldToday, IoTWorldSeries

Europe’s First Automated Gas Station Convenience Store dlvr.it/SR45J9 https://t.co/eDJDJ7CxkI

25th May 2022
IoTWorldToday, IoTWorldSeries

Zero-Emission, Autonomous Cargo Ship Under Development dlvr.it/SR3xgb https://t.co/3oU7CrKWkW

25th May 2022
IoTWorldToday, IoTWorldSeries

Hannover Messe 2022: 5 Key Themes at This Year’s Show dlvr.it/SR3wtW https://t.co/j0fQUiU2LW

25th May 2022
IoTWorldToday, IoTWorldSeries

Can AI Help Stop Mass Shootings? dlvr.it/SR3tqK https://t.co/VxPBdajWA3

25th May 2022
IoTWorldToday, IoTWorldSeries

China has revealed an autonomous marine drone carrier dlvr.it/SR3qXs https://t.co/yMiiqeMNrZ

25th May 2022
IoTWorldToday, IoTWorldSeries

ISQ’s #UAV inspection drones will be on display at this year’s @hannover_messe dlvr.it/SR35dg https://t.co/U6QOQtMbGw

25th May 2022
IoTWorldToday, IoTWorldSeries

👀 Looking to integrate #AI into your manufacturing process? Explore how #manufacturers can begin the process of… twitter.com/i/web/status/1…

25th May 2022
IoTWorldToday, IoTWorldSeries

The U.S. Army is getting a 5G boost for #AR #VR capabilities from #5G network provider @OceusNetworks.… twitter.com/i/web/status/1…

24th May 2022

Newsletter

Sign up for IoT World Today newsletters: vertical industry coverage on Tuesdays and horizontal tech coverage on Thursdays.

Special Reports

Our Special Reports take an in-depth look at key topics within the IoT space. Download our latest reports.

Business Resources

Find the latest white papers and other resources from selected vendors.

Media Kit and Advertising

Want to reach our audience? Access our media kit.

DISCOVER MORE FROM INFORMA TECH

  • IoT World Series
  • Channel Futures
  • RISC-V
  • Dark Reading
  • ITPro Today
  • Web Hosting Talk

WORKING WITH US

  • Contact
  • About Us
  • Advertise
  • Login/Register

FOLLOW IoT World Today ON SOCIAL

  • Privacy
  • CCPA: “Do Not Sell My Data”
  • Cookies Policy
  • Terms
Copyright © 2022 Informa PLC. Informa PLC is registered in England and Wales with company number 8860726 whose registered and Head office is 5 Howick Place, London, SW1P 1WG.
This website uses cookies, including third party ones, to allow for analysis of how people use our website in order to improve your experience and our services. By continuing to use our website, you agree to the use of such cookies. Click here for more information on our Cookie Policy and Privacy Policy.
X