IFA 2019 was a showcase of connected living

IFA 2019 was a showcase of connected living 4032 3024 XMOS

Berlin: 4-9 September

At Europe’s largest tech show, voice assistants were out in full force. Last year, IFA was all about smart speakers. This year, Google’s Assistant and Amazon Alexa were everywhere inside Berlin’s sprawling Messe convention centre. The two leading voice assistants were ever-present in the expo halls, integrated in a vast number of partner products and demonstrations, from soundbars and TVs to laptops and cars. Google and Amazon could have foregone their own stands and still maintained massive presence throughout the event. Bixby, by contrast, was nowhere to be seen, despite Samsung having one of the largest stands of the entire show.

Shortly before IFA kicked off, XMOS’s new 2-mic voice interface passed Amazon AVS qualification with flying colours. The XVF3510 developer kit is aimed at enabling manufacturers to embed top-performing voice interfaces into smart products at an industry-leading price. While news of the qualification arrived too close to IFA for us to create a big splash about it at the show, we did get an early mention on the Alexa Developer Blog. And we took advantage of the acoustically-challenging conference environment to give demonstrations of the XVF3510’s impressive performance in noisy conditions. A successful barge-in from a distance of 3 metres against a backdrop of 90db conference noise makes for a compelling demo, especially when you add in separate point source of music from a mobile phone for good measure.

Amazon’s smart home stand featured a range of products, including a range of 3rd party smart home products, as well as a selection of developer kits. Today more than 60,000 smart home products can be controlled with Alexa, the vast majority of which are built by 3rd parties using chips like the new XMOS XVF3510. We were invited behind the scenes to the Alexa partner drinks, where we had a chance to meet other systems integrators, ODMs and dev kit providers, including our friends from Fraunhofer and Bragi, together with several new contacts made at the event.

Smart TVs played a prominent role on the expo floor. We saw TVs with integrated smart mics from Vestel and Toshiba, while Grundig had smart mic integrated into a soundbar. Sony has packed its new Android TV with a plethora of assistants, including Google Assistant, Amazon Alexa and Apple AirPlay, giving end users the full range of services to choose from. LG has voice control with both Alexa and Google Assistant, but so far has only opted for push-to-talk. We believe the days of the remote control are numbered, and we’ll start to see more and more TVs with a built-in far-field voice interface.

Whichever way you look at it, it is clear that the Voice Market is crossing the chasm into general adoption, and we’re excited to be leading the charge in this growing ecosystem.

MWC19: are we ushering in an ‘era of intelligent connectivity’?

MWC19: are we ushering in an ‘era of intelligent connectivity’? 800 600 XMOS

February | Barcelona

It’s a bold claim to make, but after last year’s MWC Europe was described by some as a “damp squib,” this year’s theme proposed to “usher in the era of intelligent connectivity,” thrusting high-speed 5G networks, IoT, AI and big data to the forefront of discussions.

Organisers were keen to highlight ‘intelligent connectivity’ will open up a number of opportunities for highly personalised experiences. Much of the discussion was driven by developments in the connectivity infrastructure – 5G, full fibre or otherwise, advances in artificial intelligence and machine learning, and the proliferation of smart devices in the IoT ecosystem, many of which were on the tradeshow floor. To our relief, MWC 2019 also moved past the gimmicky phase of IoT – who can forget the “record everything your kids say” wearable device of 2016 or the infamous laggy smart fridge which, in low lighting, could have passed as an iPad sellotaped to a regular fridge. Swish.

The conversation has moved on to how humans are going to engage in a simple, holistic way with their smart environments. And the biggest players in the world of tech are sitting up and taking notice. The success of voice services like Alexa, Google and Siri means that consumers are questioning why they need separate remote controls or mobile apps for each piece of technology in their home when they can ask a digital assistant to close the curtains, dim the lights and cue up the film on the TV.

There is no question that public consciousness has woken up to the power of voice. Smart speakers have fueled rapid growth in the voice space and other product categories are now coming to market. Latest estimates for home consumer electronics with ‘built in’ voice assistants have been revised upwards from 2017-18 to 75.6million units – based upon increased shipments in the smart TV and media streamer categories. (Futuresource)

The power of voice

XMOS was in the Department for International Trade’s exhibition space to showcase why voice is the natural interface between human and machine, withdemonstrable use-cases. Despite the challenges associated with running voice-enabled devices in a trade-show environment (the noise equivalence to a zoo), the commercial products on display passed the ultimate test: far-field voice capture with up close accuracy.

XMOS engineering has spurred a wave of third-party product implementations that are propelling the way humans interact with their digital assistants. From a healthcare companion robot to set-top boxes, our technology is at the heart of it. Here are some of the products we had on show:

  • Freebox Delta: the brainchild of innovative French telecoms operator Free, Freebox Delta is a high-performance fusion of technologies – a set-top box, media streamer, soundbar, WiFi server and smart home hub that responds intelligently to both touch and voice. XMOS provided the far-field voice capability for its two on-board personal assistants, Alexa and OK Freebox.
  • Hello2: created by the California-based communications company Solaborate Hello2, transforms your TV into a powerful communications device that responds intelligently to touch and voice. With far-field voice capture, a 4K HDR video sensor and a six element lens, Hello2 plugs into your TV with an HDMI cable to integrate audio, video and collaboration, so you can enjoy everything from digital whiteboarding to screen sharing, media streaming and gaming.
  • Pillo: created by Boston-based Pillo Health, this companion robot redefines the role of voice-enabled assistants in the homes of the elderly, sick and vulnerable, as well as transforming the way healthcare is administered. The Pillo robot is more than just a voice-enabled pill dispenser. By harnessing artificial intelligence, the device is capable of carrying out two-way interactions with its patients, offering genuine companionship as well as assistance.

Of the many, exciting new technologies on show, we were wowed by BMW’s Natural Interaction prototype, uses voice recognition, gesture control and gaze tracking to understand what you want to do in your car without pressing a button. Our CEO Mark Lippett spoke to analyst firm Bloomberg NEF on why cars represent such an exciting opportunity for voice technology. The combination of voice, sensors and AI will deliver conceptual awareness, which opens the potential for improved safety, reduce distractions and the ability for us to connect seamlessly with our voice assistant or ‘digital twin’.

Ushering in the era of intuitive intelligence

Perhaps a more fitting theme for this year’s show would be the era of intuitive intelligence. To look at connectivity in isolation, without articulating the benefits it’ll bring to consumers, can be frustrating – particularly as big token advancements such as 5G are still on the horizon for many. Today, voice interfaces are being adopted at double the rate of mobile phones when they first appeared. They are firmly positioned for general adoption at the intersection of humans and an augmented environment – which will be supercharged by next generation networks. The ultimate goal has to be a move away from touch-based commands toward ambient computing – where our interactions with the technology around us feel intuitive and easy – and we don’t need to learn how to use it, because the intelligence is already embedded in the device.

CES 2019 | 8th – 11th January Las Vegas

CES 2019 | 8th – 11th January Las Vegas 696 401 XMOS

Going to CES? Building a voice interface into a new or existing product? Then come and see us at the show.

XMOS far field voice processors are designed for high tech, innovative device and hardware manufacturers who are looking to improve or implement a voice interface.

Join us in our private suite at The Palazzo to experience the power of voice through some of our latest commercial implementations. It’s a fantastic opportunity to see how XMOS can help with your projects. We’ll demonstrate why our far-field voice processors are optimised for edge of room and stereo devices – and we’ll also share our exciting plans for the future.

If you’d like to meet with us, we’d love to hear from you – just click on the link to request a meeting.

A roundup of our Girl Geek Dinner on 24th October

A roundup of our Girl Geek Dinner on 24th October 2000 1333 XMOS

We teamed up with the Bristol Girl Geek dinners network to host a Girl Geek event at XMOS HQ in Bristol. Over 45 people joined us to learn about the science of voice, see a little deeper into the magic of voice capture technology and find out how a virtual assistant can ‘hear’ your voice across a crowded room and execute your command.

It was a strong showcase of the talent in the South West, with female-identifying techies (and a few men) from across deep tech, finance, marketing, consulting and start-ups. The room was full of courage, easy camaraderie and razor-sharp minds, with representatives from the worlds of cyber-security, robotics, AI and imaging, together with others who are starting a business, freelance, starting a new life, studying or gone back to studying. With so energy and creativity across this space, it’s staggering that there’s still so little diversity.

Separating voice from noise

At the Girl Geek evening, we discussed how success of voice-enabled technology depends on its ability to identify when a human is talking and then isolate that voice signal from other noise such as room echo, other people talking, music and background or outside noise. This is achieved with a series of algorithms, housed on our silicon, which captures speech from across the room, cleans it up and sends the digital command to speech recognition service – such as Amazon Alexa.

Alex Craciun, our Algorithm Engineer, took us through the science of speech and explained that, if we know how speech is produced, we can extract features which model speech-like structures and from there create a speech detection algorithm to identify a speech source or a non-speech source accurately. Gwen Edwards, Director of Product Marketing, was then able to demonstrate the different techniques we use to extract human speech and clean up the digital signal – with the help of a talking lamp and an XMOS development kit that showed how far-field microphones and algorithms capture voice and strip out a cacophony of music to have a clear ‘Alexa ready’ voice command.

From understanding how this works, we then had a glimpse into the future at how other sensors (such as radar and imaging) will augment voice to make our interactions with technology more human. Once a voice assistant is able to sense our identity, mood, routine and personal preferences properly, it can start to evolve into something more meaningful – more like a trusted ‘digital twin’ or augmented extension of ourselves, than a tool to take orders.

Why are events such as Girl Geeks important?

Serrie-Justine Chapman, Founder of Women’s Tech Jobs says: “Bristol Girl Geek Dinners is a great network of over 850 members of brilliant, intelligent women. We welcome all women (or identifying as such) to the group whether already working in tech or simply tech-curious and wanting to see if there’s opportunity that might suit. I spent the majority of my career in that side of the industry, it’s dynamic, cutting edge and all about problem solving – great fun! I’m excited to watch the industry moves forward in such leaps and bounds and to see a Bristol based engineering company like XMOS being at the forefront of it all. Even more importantly, they’ve recognised the importance of encouraging women into the industry and are involving themselves in the change that’s needed. Our thanks to XMOS for a fabulous Girl Geek Dinner – everyone in the group is still buzzing from a great and welcoming evening!”

Here at XMOS, we look forward to holding more events like this one – and encouraging more women to come into (or back into) engineering and technology. The world’s changing and technology is moving at incredible speed – it’s time we Girl Geeks show just how much we can achieve!

XMOS is hiring!

If you’re interested in finding out more about what it’s like working for a leading company in the voice capture space, with partners such as Amazon Alexa and Infineon, you can browse our jobs or send us your CV with note about why you’d like to work here to work@xmos.com. We’d love to hear from you.

XMOS developers seminar 2018 | 9th June Taipei

XMOS developers seminar 2018 | 9th June Taipei 5471 3904 XMOS

In partnership with Amazon and Infineon, we designed this seminar to help our developer community understand how to optimise far-field Alexa-enabled devices.

What a turn-out! We welcomed delegates from over 50 companies. And with presentations from XMOS, Amazon and Infineon our delegates enjoyed an interactive morning learning about far-field voice capture and how to get best in class performance from our technology.

The seminar covered:

• How to build far-field Alexa voice interfaces into consumer devices
• The Alexa Voice Service architecture and latest AVS SDK features
• XMOS development kits and the optimisation tools available
• Infineon MEMs microphones and best practise for mechanical and acoustic implementation
• Getting hands-on with real-life implementations

It was followed by an exclusive lunch, hosted by Mark Lippett, CEO XMOS and all of the speakers and supporters from our partners and distributors.

Thank you to all who helped make this event possible. As anyone who organises events will know, it takes a lot of planning, pain and a little bit of magic to bring it together successfully on the day. The positive feedback from those who attended made it all wonderfully worthwhile.

Our developers’ events are by invitation only. If you’re interested in joining a future event, just enter your email address and we’ll message you with details of our latest news and upcoming events.


Grateful thanks to the wonderful event support received from from our local distributors Weikeng, Macnica and Lestina.

Computex 2018 | 5th – 6th June Taipei

Computex 2018 | 5th – 6th June Taipei 451 338 XMOS

That’s a wrap for the XMOS team and what a giant of a show this was.

Computex offered an eye-popping array of future-gazing technology. Where to start? Maybe the laptop with a touchpad that doubles as a second display – clever. Or the new PCs that are packed with powerful components – impressive. One of the things that caught our eye was the PC case with voice-controlled lighting. We’ve seen a big shift in voice enabled products since MWC and it was all on display here at Computex.
And where better place for XMOS to be than right in the middle of it all. The days passed all to quickly in a whirlwind of meetings. We met with global giants and smart start-ups – and they were all focused on voice-enabled products and the need for a more conversational human machine interface.
We showcased our VocalFusion range which offers both mono-AEC and a stereo-AEC solutions and linear and mono microphone array configurations. From our discussions with clients, it’s clear that smart speakers are still very much in demand but there’s an increasing pull for voice-enabled soundbars, media-streamers and TVs. Voice is moving to the edge of the room.

This led to some very exciting discussions around our technology roadmap. We’re working on a ‘thin-client’ solution – a game-changer, both for form factor and price point. Driving down costs while increasing implementation possibilities will help make voice ubiquitous.

And if we can readily talk to technology then we open up a world of exciting possibilities. For now though, it’s goodbye Taipei and thank you to everyone who visited with us at Computex. And maybe time for one last bubble tea.


MWC 2018 | 26th Feb – 1st March Barcelona

MWC 2018 | 26th Feb – 1st March Barcelona 1125 630 XMOS

Before they hit the post show “wall of exhaustion”, I got the teams’ reflections on this year’s MWC.

There was so much to explore and so little time to do it. With over 100,000 visitors, Mobile World Congress is still very much a showcase for the mobile communications industry. Whilst wearables made a big appearance, nothing in the mobile space felt really new and exciting.

But you didn’t have to walk the halls for long to get a sense of the huge variety of new technologies on show.

From big brands to start-ups, there’s a lot happening. Little wonder that it made such a good event for us to showcase our new technology. We launched our VocalFusion Stereo Development Kit for Amazon Alexa Voice Service – the world’s only stereo-AEC far-field solution and our second Amazon AVS qualification.

It’s a step forward in human machine interface design, delivering accurate voice capture from across the room – even in noisy environments and when the user is speaking softly. It’s designed for integration into audio-visual products, ideal for bringing voice control to stereo TVs, soundbars and set-top box products.

We also gave a sneak preview into some of the new products we have in development – which included a technology we’re developing for in-car calls and enhanced conference calling applications. This separates audio signals and spatially identifies each individual speaker of interest within a crowded noisy audio environment to capture the voice and strip out the background noise – solving what’s known as the “cocktail party problem”.

And finally, here’s one we made ourselves! Our Alexa enabled lamp made an appearance – complete with disco lights for show.

We wanted to give a real-world example of how Alexa can be integrated into everyday objects to sit helpfully and unobtrusively at the edge of the room. And it proved to be a big talking point among our guests.

The XMOS team were certainly put through their paces with a gruelling schedule of meetings with existing and potential new clients. There’s a genuine wave of excitement about the future of voice. And from where we’re standing, the view sounds great.

Thank you to everyone who popped in to meet with us. If you missed out this time, then drop us your details and we’ll make sure you’re first to know about our latest news and upcoming events.