Saturday, December 30, 2017


  1. So we can do voice over BLE-

    I wonder IF we will do voice over Zigbee, Voice over Thread?

    Dunno...will track along.

    [​IMG]
    Description

    This is a Voice over ZigBee platform. We used SPEEX voice algorithm to improve performance. Hardware was composed of ARM based MCU, mono CODEC and IEEE 802.15.4 compliant RF transceiver. VoZ Platform is suitable for two-way radio and is working on.
  2. jfieb

    jfiebWell-Known Member


    Some of this stuff has NOT been worked out yet...


    Voice over Thread

    [​IMG]
    Albert

    1 ●1
    asked May 20 '17

    Hi,

    I have a newbie question. Is it possible to implement a POTS voice quality like an intercom system using Thread (assuming all the end points are using nrf52840 SOC)?.



    [​IMG]
    Torbjørn Øvrebekk

    Nordic employee
    3576 ●2 ●7
    answered May 23 '17

    Hi Albert

    It depends on the data rate you need, as thread is not really designed for streaming applications.

    Theoretically you should be able to go up to about 128kbps between two thread nodes, but once you need to do multi hopping that drops by a factor of 2 or more.
    Secondly, we have yet to do any bench marking of our own implementation, so we can not guarantee at this point that the practice will meet the theory ;)

    In other words I am a bit uncertain if thread is suitable for reliable audio transfer.


    Best regards
    Torbjørn



    So S Johnson is at work in IoT. They will add voice to anything that can be adapted to it. Voice is SO important if they cant do voice they may use a different connection that can. Get with the times Thread?

  3. jfieb

    jfiebWell-Known Member


    Some snips- the bold text-focus on that as its very important.......


    A recent report by McKinsey estimated these devices will be responsible for contributing an estimated $11trillion in value to the global economy. Gartner predicts IoT technology will be embedded in 95 percent of new electronic product designs by 2020.

    +


    Recent advances in hardware and software technology, including multiprotocol wireless connectivity and mesh networking, make it easy to add IoT features at minimal cost to myriad products like LED lights.




    Multiprotocol technology is the future of wireless connectivity for the IoT because it mitigates the fact there is no single standard for connectivity. Devices created with multiprotocol SoCs are able to interface with smartphones via Bluetooth with low energy (LE) for device commissioning, adding or removing devices, and controlling devices on a network.


    The market trend in the IoT is to eliminate two-chip architectures with a single wireless SoC 
    capable of dynamic switching between multiple protocols while handling the end application code. A single multiprotocol SoC can timeshare the CPU, memory and RF antenna, thereby reducing the wireless subsystem bill-of-materials (BOM) cost and size by up to 40 percent.



    Could QUIK get to multiprotocal via eFPGA? Dunno

    A single multiprotocol SoC ?

    It is possible for QUIK/Nordic to partner and put their 2 chips together?


    Will track along. This item says in the future we cannot have a reference with the Eos AND the Nordic silicon, it HAS to b on
    the same silicon......




    are also bringing AI capabilities closer to the edge of the network, where IoT end nodes are growing more intelligent, enabling new applications to make critical processing and control decisions locally and with lower latency than in the cloud. The proliferation of IoT-fueled intelligence will help industries optimize productivity through predictive maintenance of factory equipment, give consumers and doctors real-time insight into biometric measurements generated by wearables, and help smart cities prevent accidents and enhance lighting and transportation efficiency. With the growing synergies between the IoT and AI, the possibilities for improving lives and transforming industries are limitless, and we are on the cusp of this revolution.


    lots more.....

    http://www.newelectronics.co.uk/ele...eving-the-vision-of-iot-in-everything/166277/



    What did I learn?

    1. Multprotocol connectivity on the same die will win?

    2. Getting a sense of the vastness of IoT. Forgetting bout smartphones.

    3. This IoT- bodes well for eFPGA too?

    a Is there a role for using eFPGA for multiprotocol? I don't know, but will learn what I can in '18.

  4. jfieb

    jfiebWell-Known Member

    New

    Amazon has multiple jobs for Zigbee, BLE mesh.

    The Echo dot +

    Amazon’s recent introduction of Echo Plus with Zigbee technology highlights the growing market acceptance of mesh technology for mainstream consumer applications.




    Zigbee is used in many smart home and connected lighting products, and also widely deployed in smart metering applications in the United States and Great Britain.


    Thread, another 802.14.5 mesh stack launched in 2015, received a big boost from its association with Nest and Google. With the market introduction of the eero Wi-Fi router, the first Thread-enabled products have hit the market.


    The introduction of Bluetooth mesh technology in July 2017 also underscores the growing momentum of mesh networking in the IoT.


    So track along. To b big in IoT QUIK needs all of these?

Friday, December 29, 2017

e·van·ge·lize
əˈvanjəˌlīz/
verb
  1. convert or seek to convert (someone) to Christianity.
    synonyms: convert, proselytize, redeem, save, preach to, recruit; More
there are 100s of jobs listed that use this word. Some tier 1 tech titans have official positions, to help a technology get a user base.
Its something a SMALL company cant do. 

Some ask what is different this time for 'lil QUIK. 
QUIK's 2 suites should be fully booked with meetings with current evaluations, engagement folks, new interested parties, the GEEKier NPD sort of folks, and on and on. They are scheduling meetings because Voice is in the church of what is happening now. It is NOT a novelty as when Alexa was first unveiled, it has moved to become the biggest thing that is the ear for AI. Voice IS the adjacent possible.

It will be one HOT ticket for all.

I have a mental model that allows for a MAJOR shift in evaluations/engagements from this show and MWC in Feb, and IoT summit in March.
  1. ronrasch likes this.

  2. jfieb

    jfiebWell-Known Member


    Here is a cocktail party invite...

    Recent Updates

    • The NPD Group
      Kick off CES 2018 with NPD! Don't forget to join us at our annual cocktail reception. Space is limited, save your spot today! http://bit.ly/2pOCyMx
      [​IMG]
      Join The NPD Group at CES 2018
      bit.ly

      As a guest at our annual cocktail reception, you'll not only get to meet and catch up with technology industry leaders from the world's top brands, you'll also gain access to exclusive NPD insights presented by our team of experienced analysts during the event.


    Do they have any interest in Alexa?


    Yes they have Ben Arnold, as follows


    Ben Arnold

    Consumer Technology Industry Analyst, Researcher, and Blogger

    Washington D.C. Metro Area
    Consumer Electronics
    Current

    he said this just the other day.....


    Smart Speaker Choices Will Multiply in 2018
    Audio brands are inviting in Alexa and Google Assistant while pitching consumers on 'hearables'—aka smart headphones

    By Allen St. John
    December 28, 2017
    Amazon Echo and Google Home land in stores next year, some industry analysts say. And the web-connected, voice-activated devices will come from traditional audio companies, too.

    Audio companies are also adding new digital chops to their headphones, with a particular focus on fitness-tracking features. And analysts say we’ll also see improvements to noise-canceling headphones, along with more completely wireless models.

    We’ll get a first look at 2018 smart speakers and headphones at CES, the giant electronics show held in Las Vegas in early January.

    Companies including Harman, JBL, and Samsung plan to introduce new products at the show. Some other top manufacturers, including Sonos and Bose, say they won’t be introducing anything new at CES—though they may launch new products later in the year.

    Here are details on what to expect from 2018 smart speakers and headphones.

    Buy Right Every Time

    Subscribe for unlimited access to ratings and reviews.
    Subscribe
    Cheaper Smart Speakers ...
    The audio world is filled with cheap wireless speakers. According to research by the NPD Group, 90 percent of the speakers sold in the U.S. cost less than $100.

    In 2018, analysts expect many speakers to add smart capabilities without getting bigger price tags.

    The tech giants “are going to make it pretty easy to license Alexa or Google Assistant with an eye toward getting it into as many homes as possible,” saysBenjamin Arnold, a consumer technology analyst with the market research firm NPD Group. “There’ll be very little price premium” for adding smart speaker technology, he says.



    I'm using this to help understand that folks like Benjamin A. has hearables front in center on their lists of things to see when they go to CES.


    And that could make smart technology an everyday feature, according to Brian Blau, an industry analyst with the Gartner research firm. “It’s hard to imagine a future in which most devices that have audio capability—speakers, headphones, headsets—won’t get [digital assistant] capability,” he says.

    That change could mean that more portable speakers will come with both WiFi and Bluetooth technology.

    Many portable speakers now only have Bluetooth, for connecting to a smartphone. But having both technologies will allow for better smart-device functionality when you’re on your home network and Bluetooth streaming when you’re out of the house.

    Consumers could even see two-part designs that combine a WiFi-enabled base paired with a portable Bluetooth satellite speaker, analysts say.

    ... And Better-Sounding Ones
    Until now, many smart speakers have had one big problem: They’ve been fine for hearing the weather forecast but leave a lot to be desired if you’re listening to Wilco or the Brandenburg Concertos.

    “So far, the smart speakers we’ve tested from Amazon and Google have been mediocre purely in terms of sound quality, with none of them earning better than a Good rating,” says Elias Arias, who leads Consumer Reports’ speaker testing. “They wouldn’t be your first choice for listening to music.”

    But that started to change late in 2017. Introduced in October, the Sonos Oneessentially added smart-speaker technology to the company’s widely sold $200 Play:1 speaker without raising the price. Several Harman speakers now have built-in support for digital assistants. And the Google Home Max, which costs $400, is targeted squarely at music lovers with the promise of high-quality audio.

    The same goes for the Apple HomePod. The Siri speaker was slated for a 2017 introduction but is now supposed to debut early in 2018. Like the Google Home Max, the $350 device is being positioned as premium audio product, with a premium price to match.

    More 'Hearables'
    The headphone industry has been rolling out a new piece of jargon in recent years. The word “hearables” isn’t clearly defined, but it refers to headphones that perform digital magic beyond playing music.

    A number of these work as fitness trackers. For instance, the Jabra Elite Sport and Jabra Sport Coach both count exercise reps and steps, and talk you through your workout while running through your playlist. Along with several other headphones, the Elite Sport has a heart-rate sensor. And more choices for fitness-tracking headphones are coming in 2018, analysts predict.

    In addition, a number of headphones now offer customized noise cancelation. The highly rated Bose QuietControl 30 and Sony MDR-1000X headphones, launched in 2016, were two of the first headphones to let users adjust the level of noise cancelation, making it easier to hear airport announcements or sirens, for instance. More of these headphones came on the market in 2017, and their ranks are likely to grow in 2018.

    A more cutting-edge “hearable” feature is translation between languages. Along with conventional tasks, the Google Pixel Bud can work with the company’s Pixel phones to provide translations of simple conversations among dozens of languages. “And I think you’ll see [more translation products] showcased this year,” says Blau, the Gartner analyst.

    Some manufacturers, such as Nuheara with its IQbuds, also claim their products are useful simply for filtering out background noise and making it easier to hear conversations. Such products “could be almost like hearing aids for people who can hear fine,” says Arnold, the NPD Group analyst.

    And they’ll join other products already blurring the boundary between entertainment and hearing enhancement. Some sound bars and TV settings are meant to make it easier to hear television dialog. And many prescription hearing aids can access musicstreaming services through a Bluetooth connection to the user’s phone.

    Decline of the Wire
    If you go shopping for headphones in 2018, there’s a good chance you’ll end up with a wireless model, one that connects to your phone by Bluetooth.

    “They’re taking over the category, because in 2017 we’ve seen even more companies remove headphone jacks from smartphones,” says Ross Rubin, principle analyst for Reticle Research, a market research firm.


    Taking that trend a step further, look for more truly wireless earbuds, such as the Apple AirPod, Bluetooth models where the earpieces aren’t even tethered to each other. There were just a handful of truly wireless models available in 2017, but that’s likely to change in 2018.

    “I think we’ll all benefit from fewer wires in our lives,” Blau says. “They get in the way, they tangle, and they break.”

    Audio companies hope that new wireless models, along with “hearable” technology, will persuade consumers to amass a personal quiver of headphones.

    “I’ve got a pair for my office, a pair for exercise, and a pair for the plane, and they don’t cross over,” Arnold says. “Apple, Beats, and Sony are trying to tell that story that you need different headphones for different listening environments.” 

    Whether that’s true, of course, is up to consumers.

Thursday, December 28, 2017

Valencell to Showcase New Biometric Sensor Technology in Wearables and Hearables at CES 2018
by Ryan Kraudel | Dec 14, 2017 | Press |

Valencell will demonstrate how accurate wearable biometric sensors are redefining traditional views of wearable form factors and use cases across multiple industries, from consumer to medical to industrial, and more

Raleigh, N.C. (Dec. 14, 2017) – Valencell, the leading innovator in performance biometric sensor technology, today announces its plan to debut new software and hardware technology, as well as new use cases in conjunction with its strategic partners at the Consumer Electronics Show 2018 (CES 2018). Wearable biometric sensor technology is being integrated within many different types of devices beyond just smartwatches and sports earbuds, including construction hardhats, virtual reality (VR) solutions for pain management in healthcare, and long-haul trucking solutions to combat drowsy driving. The technology and its wide array of use cases will be showcased at Valencell’s CES booth Tuesday, January 9 through Friday, January 12, located in the Sands Expo, Level 2, Halls A-D at the Venetian in booth #43809.

Valencell president and co-founder Steven LeBoeuf, Ph.D. will be speaking at the FitnessTech Summit on a panel called “Data Delivery: Accelerating the Winding Road,” where Dr. LeBoeuf and his co-panelists will discuss how devices are gathering more information than ever, but what are they telling us and how reliable is the output being delivered? Dr. LeBoeuf will also deliver a solo presentation at the FitnessTech Summit on the wearable data ecosystem and how accurate sensor data drives valuable user experiences in numerous industries.

Dr. LeBoeuf will also be speaking at the Wearable Technologies Summit at CES 2018. He will be interviewed in a “fireside chat” titled “The Community of Wearables: From ‘Me’ to ‘We’”. The session will discuss the proliferation of wearable technology beyond just smartwatches and fitness bands.

“While Valencell continues to be the forefront of the wearables and hearables market, we are simultaneously researching and developing innovative use cases for our highly-accurate biometric sensor modules,” said Dr. Steven LeBoeuf, president and co-founder of Valencell. “We’ve met consumer and partner demand for smaller, more power efficient technology in the wearables and hearables space and we will continue to meet those demands while exploring new areas where our technology can bring value such as medical and industrial cases.”

In addition to the product announcements Valencell will be making during CES in January, Valencell will debut an innovative, original booth layout to showcase key partners and use cases, including Sports & Fitness, Health & Wellness, Medical and Enterprise & Industrial:

  1. Sports & Fitness: This area of the booth will focus on using wearables to improve fitness levels and sports performance.Professional athletes will be onsite working out with a Scosche Rhythm+™ armband, with their data being streamed live to a performance screen. Additionally, Valencell and Firstbeat have partnered to create meaningful user experiences in biometric wearables and hearables and will be demonstrating heart rate, training effect and recovery, among other metrics.
  2. Medical: Valencell will demonstrate the latest advancements in its PPG-based, cuff-less blood pressure sensing technology. Additionally, Valencell will demonstrate advancements in its R-R interval technology enabling the detection of chronic conditions such as atrial fibrillation and arrhythmia. Valencell will also be demonstrating the use of its technology in combination with VR for pain management applications from Firsthand Technology, which has shown the ability to significantly reduce acute and chronic pain without opioids.
  3. Health & Wellness: Valencell will demonstrate the advancements its newest hardware and software updates have made in sleep monitoring and stress management as they continue their innovation to move the industry beyond the “10k steps” myth to explore more meaningful insights from biometric sensor data.
  4. Enterprise & Industrial: Valencell’s growth into new industries continues as they strategically partner with companies who are seeking to leverage biometric sensor technology to improve safety in the workplace. Valencell and Bodytrak will demonstrate their technology that not only monitors heart rate but real-time core body temperature. Valencell and KOS Technology will partner to demonstrate their collaborative technology that helps detect and alert drowsy drivers in a long-haul trucking setting.
“Firsthand selected Valencell technology in the development of our groundbreaking VR for pain management application because we know the importance of accurate biometric sensor technology when using virtual reality to manage pain,” said Howard Rose, co-founder and CEO of Firsthand Technology. “Valencell’s commitment to applying its biometric sensor technology to new use cases, especially in the medical field, has made for a collaborative partnership with Firsthand that has allowed us to address the national issue of pain management in an innovative way.”

Valencell and its partners will be showcasing their latest technology and use cases at Valencell’s CES booth December Tuesday, January 9 through Friday, January 12 located in Tech West, Sands Expo at the Venetian in booth #43809. To schedule a media briefing please contact valencell@maxborgesagency.com. For more information on Valencell, please visit www.valencell.com.
  1. .
  2. jfieb

    jfiebWell-Known Member

    New



    I always reread the key thing of S Johnson's book

    SPEED SUMMARY: WHERE GOOD IDEAS COME FROM – THE NATURAL HISTORY OF INNOVATION
    • 3
    [​IMG]

    Where do good innovation ideas come from?

    The short answer; coffee houses.

    Longer answer, from the seven places listed below.

    From a review of 189 great ideas from pencils to parachutes, best-selling business and popular science author Steven Johnson traces the history of successful innovations to identify where good ideas come from – and where they don’t.

    First, where good ideas don’t come from.


    Good ideas do not – for the most part – come from inside someone’s head. Instead, they come from outside – specifically from social interaction. A study conducted in leading research laboratories found that scientists rarely, if ever, had a flash of inspiration or eureka moment alone in the lab. Instead, ideas happen in conversation with colleagues. So want a great idea? Then go to a coffee house and talk with someone.


    Please post more!


    So want a great idea? Then go to a coffee house and talk with someone.

    Nor do good ideas come from thoughts or visions. Instead, they come from stuff. Every great idea is a combination or mutation of an idea that has already been brought to life. Ideas brought to life in products that are already out there are the building blocks of innovation – not thoughts.

    Finally, good ideas do not come from looking forward or back, rather they come from looking left and right, to what is adjacent to us. Johnson builds on Stuart Kauffman’s concept of the ‘adjacent possible’ to reaffirm that tomorrow’s great innovations are built from the stuff of today – specifically from the things around us that can be combined into something new.


    This is why M & A will have some urgency now. They need it on the bench. You can see Kauffman at work in 'lil QUIK. How things have changed as they move into Voice over BLE, and Zigbee most recently


    “The strange and beautiful truth about the adjacent possible is that its boundaries grow as you explore them. Each new combination opens up the possibility of other new combinations”.

    Seven Questions for Finding Good Ideas
    Based on a review of good ideas brought to life as innovations, Johnson suggests that there are seven specific places to look where you’ll find the seeds of a great idea. Importantly, they’ll not be found where you are right now. Changing up your environment, and exposing yourself to new ideas is key. But one in a new space, the ‘places’ where your good ideas will come from are seven principles that can be formulated as seven questions to ask yourself – and your colleagues.

    1. What new possibilities are there today, that didn’t exist a year ago? (principle of adjacent possibilities)
    2. What hunches have you had for some time about what to do)? (principle of slow hunches – the more others share them or build on them, the better they may be)
    3. What do fresh eyes think we should do (principle of liquid networks)
    4. What’s worked that’s surprised us? (principle of serendipity – build on what surprises, chance happenings)
    5. What’s the biggest learning from our biggest error? (principle of error)
    6. What other purpose can our product or service be used for? (principle of exaptation – bird feather evolved for warmth, and then through ‘exaptation’ they became wings)
    7. What big success can we build on? (platform principle)
    For us as individuals, Johnson summarises his insights for how we can increase the chances we’ll participate in evolving good innovation ideas

    “The patterns are simple, but followed together, they make for a whole that is wiser than the sum of its parts. Go for a walk; cultivate hunches; write everything down, but keep your folders messy; embrace serendipity; make generative mistakes; take on multiple hobbies; frequent coffeehouses and other liquid networks; follow the links; let others build on your ideas; borrow, recycle, re-invent.”


    understand all of the above and know that QUIK is alive in the adjacent possible. THat on the right side of Moores law the Eos S4
    will be built with ideas from a liquid network, they will let others help shape it,

    they can't do M & A, buy they can partner and have a BLOG that says there will be MORE of that in '18.



    PS It was a good day when I decided to let Johnson's ideas be my guide for evaluating how QUIK was /is doing?

XMOS

Discussion in 'Main Forum' started by jfieb15 minutes ago.
  1. jfieb

    jfiebWell-Known Member


    The far-field audio detection technology from XMOS is being used in several products such as the Martina smart assistant from Pegatron to identify voice commands accurately across a room.

    “Voice-controlled human-machine interfaces will be a dominant conversation at CES”


    It is also showcasing the VocalFusion Stereo Evaluation Kit (XK-VF3500-L33) – the world’s first stereo acoustic echo cancellation (AEC) far-field linear microphone array solution. The XVF3500 voice processor in the kit allows two-channel full duplex AEC for developers of smart TV, soundbar, set-top box and digital media adapters.

    [​IMG]“The huge growth in advanced voice-controlled smart speakers – Amazon Alexa, Google Home, Apple HomePod – means that voice-controlled human-machine interfaces will be a dominant conversation at CES”, Mark Lippett (pictured right) President and CEO at XMOS tells us.

    “For us, it’s about making the best user experiences, with the least intrusion into our living spaces. Not only do we deliver the highest quality voice capture and audio playback across the noisiest rooms, but our products also enable the technology to merge into the existing flat surfaces already in our environment.

    “We currently have the only Amazon AVS qualified development kit with a far-field linear mic array and during the show we’ll be demonstrating the world’s first stereo-AEC far-field linear mic array solution – both capable of delivering ‘across the room’ voice interfaces.

    “At CES, companies will be looking for next generation, seamless HMI – natural language interfaces that are ready for mass-market adoption and we are proving that our technology can deliver that now.
  2. jfieb

    jfiebWell-Known Member

    New

    XMOS is part Sensory IP



    XMOS and Sensory partner to deliver keyword detection for the Internet of Things
    Partnership combines embedded speech capture with proven voice control technologies.

    Bristol, United Kingdom and Santa Clara, Calif., 1st November 2016 – XMOS Ltd., the leader in voice hardware solutions and Sensory Inc., a Silicon Valley company that enhances the user experience and security of consumer electronics, have today announced a partnership to deliver Sensory's TrulyHandsfreeTM voice control technology on the XMOS xCORE-VOICE far-field voice capture processing platform.

    TrulyHandsfree is the latest generation of voice keyword detection software from Sensory, the recognized leader in the speech industry. It provides high accuracy and robust performance in noisy environments, and enables a more secure user experience.

    The xCORE-VOICE platform delivers microphone aggregation combined with sophisticated voice processing and a flexible interface to automatic speech recognition systems.

    Commenting on the partnership, Todd Mozer, CEO of Sensory said, "XMOS is driving new levels of integration and performance in the voice processing market. The combination of its hardware and software solution platform with our TrulyHandsfree technology delivers a potent combination into this rapidly expanding voice-enabled market."

    Mark Lippett, XMOS CEO added, "We are delighted to partner with Sensory to integrate its industry-leading keyword detection technology as part of the xCORE-VOICE solution. We expect our partnership to help drive the adoption of voice interfaces across a wide range of consumer products."

    About XMOS

    XMOS is a leading provider of voice interface solutions. Now on its second generation, the xCORE-200 family of Multicore Microcontrollers is pushing the boundaries of quality and integration - delivering the most comprehensive Voice User Interface (VUI) controller solutions for IoT devices. For more information, please visit www.xmos.com.

    About Sensory Inc.

    Sensory Inc. creates a safer and superior UX through vision and voice technologies. Sensory's technologies are widely deployed in consumer electronics applications including mobile phones, automotive, wearables, toys, IoT and various home electronics. With its TrulyHandsfreeTM voice control, Sensory has set the standard for mobile handset platforms' ultra-low power "always listening" touchless control. To date, Sensory's technologies have shipped in over a billion units of leading consumer products. Visit Sensory at www.sensory.com
  3. jfieb

    jfiebWell-Known Member

    New

    I enjoy ALL of the blogs of the companies alive with the adjacent possible of voice.

    Todd Mozer- 5 stars for his thoughts. He did Neural network speech 2o yrs ago.

    Here is xmos most recent entry


    How voice user interfaces will feature in CES 2018
    Posted: 21 December 2017
    XMOS Editor
    By:
    [​IMG]
    The recent rise of the smart speaker has been exceptional, and all signs suggest the dominance of Amazon's Alexa and to a lesser extent Google Home is set to continue at CES 2018. Looking at the increase in searches made for these devices (see graph below) we can see how demand has grown and that we're now at a point where there is exceptional competition between the major players. And this is before Apple's HomePod, which starts shipping early next year, joins the fray.

    Three years ago we were already at the point where 55% of teens and 41% of adults use voice search more than once per day on their mobile phones (source Google Survey). The rise of the Echo and Google Home has only increased this.

    The work that we've been doing with Amazon Alexa Voice Service (our VocalFusion 4-mic technology is the first - and currently only - linear far-field mic array qualified by Amazon for the Alexa Voice Service) and other Tier 1 partners worldwide suggests that these devices are just the tip of the iceberg. We firmly believe that while there will be a plethora of similar devices,



    the real and very considerable growth is going to come from innovation, not replication.

    [​IMG]
    Moving to the edge of the room
    2018 will see voice technology integrated into a greater range of systems than just smart speakers. This is partly a natural step as AI chips and edge computing improve; but also as a consequence of the need to integrate these into multiple rooms, and locate them in positions where they can be used, regardless of where the voice user interface is and the direction they're facing.

    Take a closer look at almost any advert for a smart speaker, from any vendor, and more than likely you won't see a power cable, and it will be positioned in the centre of a room - a coffee table, or a kitchen counter, far away from a power socket.

    By integrating smart far-field voice user interfaces into multiple wall-mounted and edge-of-room systems, the technology can be more easily brought into the home, and added to products we already use. Will we see a smart dishwasher or washing machine with a voice UI? Probably not yet, but there is already a smart thermostat with built-in Alexa Voice Service, the ecobee4. Will we see a voice enabled TV, soundbar or media streamer? Absolutely because the technology is now available to add voice interfaces to products with stereo output channels.

    What you can expect to see from us at CES
    During CES in January, XMOS will be demonstrating our latest voice interface technology. Our technology will also be in evidence on several partner stands on the show floor, for example the XMOS XVF3000 voice processor is used in both the Bocco robot on the Yukai Stand (64601 in "Creative Vision, Japan Tech".

    [​IMG]
    VocalFusion Stereo Evaluation Kit (XK-VF3500-L33),
    with VocalFusion XVF3500 Voice Processor

    We'll be showcasing our new VocalFusion stereo linear kit, the world's first stereo-AEC linear far-field voice kit for smart devices. This uses the new XVF3500 voice processor, which delivers 2-channel full duplex acoustic echo cancellation (AEC) - targeted at OEMs working in smart TVs soundbars, set-top boxes and digital media adaptors.

    We'll also be showing our VocalFusion 4-Mic Kit for Amazon AVS along with the XVF3100-based VocalFusion Linear Kit, both designed for the edge of room segment for integration into smart panels, kitchen appliances and industrial equipment.

    Looking forward, there'll also be demonstrations of our VocalSorcery advanced blind signal separation, which delivers voice capture from individual people within noisy environments like a café or car, and a joint proof of concept with Infineon that blends data from radar and microphones with XMOS voice capture technologies to deliver a more seamless human machine interface that enables greater context for the systems.

    To arrange to meet the XMOS team visit xmos.com/news/events


    Steven Johnson's work- expect multiples. Sensory is so great, but there is Rubidium,
    QUIK has made me a proud part owner as they chose voice with limited resources in 15.
    There should soon be others ( many)

    In 18 voice is SO HUGE. It is the input into AI.

    M& A will be in earnest- IF Nest needs something to try to fend off AMZN they will just buy it.
    You tend to use what you have on your bench.
    No dithering will be allowed- they have to innovate-
    they have to do it ASAP.

    Will track along