HEAR ME -
Speech Blog
HEAR ME - Speech Blog  |  Read more March 11, 2019 - Taking Back Control of Our Personal Data
HEAR ME - Speech Blog

Archive for the ‘Press Releases’ Category

HMD Global Selects Sensory to Secure Nokia Smartphones with TrulySecure Face ID

February 27, 2019

TrulySecure is Sensory’s class-leading on-device facial recognition solution found in top-selling smartphones from leading brands and more than three dozen banking apps

BARCELONA and SANTA CLARA, Calif., – Feb 27, 2019 – Sensory, a leader in speech and vision technologies that enhance the user experience and security of consumer electronics, today announced HMD Global, the home of Nokia phones, has integrated TrulySecure facial recognition into three of the Nokia smartphones it has launched at MWC 2019. As deployed, TrulySecure allows Nokia 9 PureView, Nokia 4.2 and Nokia 3.2 users to unlock their phone via powerful facial recognition.

TrulySecure is a FIDO Certified™ biometric authentication technology that quickly, conveniently and securely recognizes enrolled users via powerful face biometric recognition technologies. Featuring the latest in Sensory’s embedded AI technology, TrulySecure can identify and authenticate enrolled users in less than a second and differentiate individuals at a 99.999% accuracy rate. Boasting industry-leading on-device liveness detection and anti-spoofing algorithms, TrulySecure makes it nearly impossible for an imposter to gain access to a protected device or app. Mitigating the security concerns of competing facial recognition technologies, TrulySecure runs completely on device, stores biometric profiles as highly encrypted irreversible code, and never sends biometric data over the internet.

“Data and device security are extremely important decision factors when it comes to purchasing a smartphone,” said Todd Mozer, CEO at Sensory. “We’re excited to be working with HMD Global to outfit the latest Nokia smartphones with powerful on-device facial recognition-based authentication. Our technology offers users an extremely convenient means of unlocking their devices and apps, while offering extreme protection against intruders.”

For more information about this announcement, Sensory or its technologies, please contact sales@sensory.com ; Press inquiries: press@sensory.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 TrulyHandsfree™ 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.

 

Sensory Named #5 on Fast Company’s Most Innovative Companies 2019 List

February 20, 2019

Sensory for its ‘AI at the Edge’ technologies take top ten spot in the 50 most innovative companies list

Santa Clara, Calif., – February 20, 2019 – Sensory, a Silicon Valley-based company focused on improving the user experience and security of consumer electronics through state-of-the-art embedded AI technologies, today announces its inclusion in Fast Company’s “World’s Most Innovative Companies 2019” edition. Sensory ranked as the fifth most innovative company in the Consumer Electronics category. Last years top 5 innovative companies in the consumer electronics categories included Apple, Amazon, Nintendo, Peloton and Sony.

“It is a tremendous honor to have made Fast Company’s ‘World’s Most Innovative Companies’ list this year. Sensory has been helping great companies like Amazon, Google, LG, Motorola, Plantronics, Samsung and many others create highly innovative products, so it’s nice that the core technology behind the innovation is being recognized,” said Todd Mozer, CEO at Sensory.

Since its founding in 1994, Sensory has pioneered the use of neural networks for on-device AI, with a variety of technology offerings, including natural language recognition, wake words, large vocabulary speech recognition, computer vision and biometric authentication. In the early 2010s, Sensory started the voice revolution by enabling the first completely hands-free, wake word enabled smartphone, the Moto X. This was the first time a wake word activated voice assistant was engineered for low-power operation on a mobile device.

Fast forward to 2019, Sensory has become the global leader in enabling voice assistants, having shipped its TrulyHandsfreeTM technology in more than two billion smart assistant devices around the world, and more than 3 billion devices and apps total. Beyond wake words and voice command and control, Sensory has also made it possible to move face and voice authentication processing from of the cloud to the edge with its TrulySecureTM technology, making face or voice authentication faster, safer and more secure. Today Sensory is bringing edge-based natural language voice interaction to cars, consumer electronics, apps and more with TrulyNaturalTM, a powerful, small footprint speech recognition engine capable of natural language recognition. This technology will enable app developers and device makers to integrate a fully voice-controlled natural language user experience into their products without ever sending user voice data over the internet – ensuring total user privacy.

With Sensory’s technology having shipped in more than two-billion product globally, the company has solidified its position as a market leader for AI-at-the-Edge solutions, and continues to raise the bar for performance, accuracy and user experience in all of its product categories.

This year, Fast Company’s editors and writers sought out groundbreaking businesses across 35 industries and every region. They also judged nominations received through their application process.

The World’s Most Innovative Companies is Fast Company’s signature franchise and one of its most highly anticipated editorial efforts of the year. It provides both a snapshot and a road map for the future of innovation across the most dynamic sectors of the economy.

Fast Company’s Most Innovative Companies issue (March-April 2019) is now available online at https://www.fastcompany.com/MIC, as well as in app form via iTunes and on newsstands beginning February 27th. The hashtag is #fcmostinnovative.

For more information about this announcement, Sensory or its technologies, please contact sales@sensory.com; Press inquiries: press@sensory.com.

About Sensory
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. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNatural large vocabulary natural language embedded speech recognition. Sensory’s technologies have shipped in over a billion units of leading consumer products.

TrulyHandsfree, TrulyNatural, TrulySecure and VoiceGenie are trademarks of Sensory Inc.

About Fast Company’s Most Innovative Companies
Since 2008, Fast Company’s Most Innovative Companies has been the definitive source for recognizing the organizations that are transforming industries and shaping society. Last year, Fast Company recognized 350 organizations with this prestigious honor, from the largest companies in the world to small startups with just a few employees.

Sensory Acquires Vocalize.ai for Speech Technology Testing Capabilities

February 13, 2019

Vocalize.ai to remain independent source for benchmarking speech products and technologies

Santa Clara, California, – February 13, 2019 – Sensory Inc., a Silicon Valley company that pioneered speech recognition and AI in consumer electronics today announced the acquisition of Vocalize.ai, a software tools and services company that performs benchmarking, accuracy assessments and bias evaluations for speech technologies and natural language interfaces. As part of the acquisition, Sensory will maintain Vocalize.ai as an independently operated division.

According to Sensory CEO Todd Mozer, “Sensory has always done in-house technology testing through simulations. However, we saw a growing need for an independent testing source that wasn’t influenced by our data or testing methods, that could also provide more real world, black-box testing. Vocalize.ai offers exactly what we needed and was in fact tremendously helpful in shaping our new TrulyHandsfree 6.0 release.”

There has always been a gap between the testing that technology companies do in simulated environments and the real world performance of the end product when the right microphones, product housing, memory and MIPS constraints, and sound processing technologies are added. Vocalize.ai helps to close this gap with the ability to assess technology and product performance.

Joe Murphy, Vocalize.ai CEO said, “As more companies add voice to their products, there is growing need for an independent evaluation service and software tools that ensure a quality user experience. It’s exciting to have access to the deep bench of AI and machine learning talent and resources of Sensory. It is also important to recognize that Vocalize.ai will operate as an independent company under the Sensory umbrella. In this model, we will continue to provide quality evaluations and competitive benchmarking services for the entire voice-enabled industry.”

Sensory’s clients will benefit from this new relationship through discounts on Vocalize.ai services, and they will be given the option to include the testing services offered by Vocalize.ai throughout the product development process. “Our goal is to maximize the performance of our technologies, while ensuring the best possible user experience on our customers’ products! There was only so far we could take things with the technology in isolation. We believe our customers will see great value in being able to test our technologies as deployed in real-world product environment,” added Mozer.

For more information about this announcement, Sensory or its technologies, please contact sales@sensory.com; Press inquiries: press@sensory.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 TrulyHandsfree™ 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.

TrulyHandsfree are trademarks of Sensory Inc.

Sensory Releases Embedded AI That Allows Voice Assistants and IoT Devices to Identify a Wide Variety of Home Sounds

January 7, 2019

TrulySecure Sound ID identifies sounds within the home and can send messages to homeowners

Santa Clara, Calif., January 7, 2019 – Sensory, a Silicon Valley-based company focused on improving the user experience and security of consumer electronics through state-of-the-art embedded AI technologies, today announces TrulySecure™ Sound ID, a major breakthrough for cloud-free always listening AI that gives devices the ability to identify a variety of common and critical sounds within the home, and intelligently interpret if action needs to be taken, without the security risk of sending audio recordings to the cloud for processing.

Backed by Sensory’s 25 years of experience developing practical applications for neural networks and deep learning, TrulySecure Sound ID is capable of recognizing a variety of environmental sounds, including glass breaking, babies crying, dogs barking, home security alarms, smoke/CO alarms and low battery warnings, doorbells, knocking, snoring and more. Consumer devices could instantly warn users when these sounds occur and send the owner sound clips to better understand the situation.

“With so many voice-controlled products entering our homes, we saw an excellent opportunity to enable the microphones in these devices to do more than just listen for wake words and recognize speech,” said Todd Mozer, CEO of Sensory. “With TrulySecure Sound ID, we’re making it possible for companies to create smart always-listening products that can alert us of things happening within our homes that we may not hear, and safeguard our home and family from potentially dangerous situations.”

Sharing the same distinguished qualities that make Sensory’s ‘AI at the Edge’ technologies industryleading, TrulySecure Sound ID boasts performance and privacy by performing all analyses on device. By training each specific sound profile on thousands of real-world samples, similar to how Sensory trains biometric recognition, TrulySecure Sound ID takes several discriminate factors into account when processing sounds. Sound ID learns each sound type utilizing an approach that combines deep learning model training with proprietary discriminant learning techniques, the two approaches combined produce a superior solution than either approach could achieve in isolation.

Sound ID is available today as a component of Sensory’s TrulySecure Speaker Verification (TSSV) suite of
AI solutions for smart speakers and IoT devices. Ideal for enabling smart assistants, TSSV combines:

  • Text dependent and text independent voice biometric recognition for user ID and authentication
  • Always listening wake word recognition
  • Seamless voice enrollment
  • Sound ID

All of the technologies in TSSV pose no privacy or security concerns because they run completely on device and never touch the cloud. TSSV supports all major operating systems and is hardware agnostic, offering nearly limitless implementation flexibility. Additionally, Sensory can customize TSSV to match the exact needs of its customers, enabling only the sound profiles required for specific use cases.

For more information about this announcement, Sensory or its technologies, please contact
sales@sensory.com; Press inquiries: press@sensory.com.

About Sensory
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. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNatural large vocabulary natural language embedded speech recognition. Sensory’s technologies have shipped in over a billion units of leading consumer products. 

TrulySecure is a trademark of Sensory Inc.

Sensory Releases Cloud-Free Voice Control for Bluetooth Speakers – Maintaining User Privacy

January 7, 2019

Designed to not invade user privacy or record user conversations, Sensory’s VoiceGenie Smart Speaker reference design is a low-cost solution for enabling voice-powered music control on Bluetooth speakers

Santa Clara, Calif., January 7, 2019 – Sensory, a Silicon Valley-based company focused on improving the user experience and security of consumer electronics through state-of-the-art embedded AI technologies, today announces a new solution that will allow Bluetooth speaker manufacturers to create exciting new products that feature voice-activated control of music with branded wake words, without needing any special apps or a Wi-Fi connection.

“When I watch how my family uses our Amazon Echo, my kids just stream from their phones and use it more like a Bluetooth speaker, with occasional voice commands to play or stop. They don’t use a lot of complex requests because they always have their phone with them and most of the music controls are from their phone,” said Todd Mozer, CEO at Sensory.

Today’s smart speakers with voice assistants like Alexa, Google, and Siri give users an all or nothing choice between control (mic on) or privacy (mic off) – there is no in-between. Sensory’s VoiceGenie Smart Speaker reference design enables an in-between option for simple hands-free voice controls, but all done on device with nothing sent to the cloud. This means users’ private data won’t be stored somewhere that it can be accessed or sold. It also means conversations can’t be accidentally recorded and sent out. As an added bonus to consumer electronics manufacturers, Sensory can create custom branded wake words that support the speaker OEM’s own brand rather than the wake word from a third-party voice assistant that is often a competitor.

“Many consumer electronics OEMs want to get into the fast-growing market for smart speakers, but they don’t want to use another brand’s wake word or risk their customers’ privacy and personal data to do so. Sensory now has an affordable solution that offers these companies access to a user-friendly voice UX for Bluetooth speakers that maintains their brand’s integrity and doesn’t require access to cloud-based AI processing,” Mozer continued.

Sensory’s new VoiceGenie Smart Speaker Reference Design offers a number of advantages to product
OEMs and their customers, including:

  • Easy set up. No more complex than a simple Bluetooth device
  • Simple easy to use voice commands for basic music player functions (volume, next song, play, pause, etc.)
  • Works with all locally stored music and streaming music apps through standard Bluetooth protocols
  • No special apps or hardware required on connected smartphones
  • Proprietary AEC optimized for speech recognition allows voice barge-in when audio is playing
  • Low cost system design with fewer components than a WIFI speaker, no WIFI radios required

Sensory is offering an early developer program to make it fast and easy to bring voice-controlled Bluetooth speakers to market, and the program includes custom wake word development, source code application support, pre-configured recognition sets, customer support and a go-to-market license.

Sensory’s ‘AI at the Edge’ technologies are all designed to make consumer electronics smarter through always-listening wake words, speech and natural language recognition, face and voice biometrics and a variety of computer vision technologies, without the associated privacy risks associated with cloudbased AI. All of Sensory’s core AI technology suites, including TrulyHandsfree, TrulySecure and TrulyNatural, are embedded on device, and all processing is done locally, allowing these technologies to offer industry-leading accuracy, performance and user experience, without compromising user privacy and data security.

For more information about this announcement, Sensory or its technologies, please contact
sales@sensory.com; Press inquiries: press@sensory.com.

About Sensory
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. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNatural large vocabulary natural language embedded speech recognition. Sensory’s technologies have shipped in over a billion units of leading consumer products. 

TrulyHandsfree, TrulyNatural, TrulySecure and VoiceGenie are trademarks of Sensory Inc.

Universal Electronics Teams Up with Sensory to Deliver Smart Home Digital Assistant Platform with Embedded Voice Control and Branded Assistant Experience

January 4, 2019

By Fusing UEI’s Nevo® Butler Smart Home Hub (Powered by nevo.ai) with TrulyHandsfree Speech Recognition from Sensory, UEI’s Customers are Able to Create Powerful Voice-Enabled Digital Assistants that Feature Brand-Specific Wake Words and Cloud-Free Voice Control

 

Santa Ana, CA – January 4, 2019Universal Electronics Inc., (UEI) (NASDAQ: UEIC), the worldwide leader in universal control and sensing technologies for the smart home, today announced that it will be pairing its digital assistant platform for the smart home, codenamed Nevo® Butler, with TrulyHandsfree™ voice command capabilities as well as customer-branded wake words from Sensory, the leader in on-device speech recognition and wake word AI.

 

Nevo® Butler is an end-to-end voice-enabled smart home hub with built-inwhite label digital assistant that unifies entertainment control and home automation experiences, enabling interoperability across fragmented ecosystems. Powered byQuickSet® Cloud, Nevo Butler delivers a versatile monitoring and control assistant solution for the home, capable of addressing a wide range of devices and use cases, ranging from voice control of an existing installed base of devicesto innovative new Cloud services. With a customizable digital assistant front-end,enterprise-level integration services and an expanding ecosystem of add-on services, this platform allows service providers and consumer electronics brands to bring voice-enabled services to their customers under their own brand name while remaining in control of the consumer relationship.

 

Available as kits that address specific channel needs, Nevo Butler can be bundled with a range of certified devices including Ecolink® sensors, offering safety and security, energy management and hospitality applications, in addition to voice-enabled universal entertainment control.

 

“This exciting new platform integrates our latest QuickSet Cloud services with our nevo.ai white label digital assistant platform, as well as back-end enterprise integration services required for large-scaleIoT fleet management. This product gives our customers a powerful platform to offer innovative and new voice-powered services to consumers while they remain in charge of the consumer experience.” said Arsham Hatambeiki, SVP Product and Technology for Universal Electronics Inc. “Sensory’s voice recognition capabilities provide a reliable foundation to build new digital experiences in the home that consumers will trust and use on a daily basis.”

 

TrulyHandsfree is the most widely deployed embedded speech recognition engine in the world, having enabled a hands-free voice user experience on more than two billion devices from leading brands worldwide. TrulyHandsfree offers support for every voice UI application with several types of wake word options, such as independent fixed wake words, user-enrolled fixed wake words, and user-definedwake words. UEI and Sensory will provide customers the ability to create custom speaker independent wake words for their Nevo Butler-powered smart assistant devices.

 

“TrulyHandsfree was purposefully engineered to offer extremely accurate and noise robust wake word and speech recognition on devices with ultra-low-power configurations to very high-performance components,” said Todd Mozer, CEO of Sensory. “TrulyHandsfree’s limitless design flexibility, unrivaled platform support and vast customization options make it is the ideal solution for UEI’s service provider and electronics manufacturing customers that want to create new smart assistant solutions that feature branded wake words and cloud-free voice control.”

 

Sensory’s TrulyHandsfree supports US English, UK English, Arabic, Dutch, French, German, Italian, Japanese, Korean, Mandarin, Portuguese, Russian, Spanish, Swedish and Turkish. The TrulyHandsfree SDK is available for Android, iOS, Linux, QNX and Windows. Sensory provides developer support for cloud service interfaces on Linux, Android, iOS and Windows as well as support for dozens of proprietary DSPs, microcontrollers, smart microphones, andother low-power embedded devices.

 

Additionally, ultra-low-power deeply embedded ports of TrulyHandsfree are available for leading DSP/MCU IP cores from ARM, Cadence, CEVA, NXP, Synopsys and Verisilicon, as well as for integrated circuits from Ambiq Micro, Analog Devices, Cirrus Logic, DSP Group, Fortemedia, Intel, Knowles, Microchip (Microsemi), NXP, Qualcomm, QuickLogic, Realtek, Synaptics, STMicroelectronics, TI, Yamaha, and XMOS.

 

For more information about this announcement, or UEI, please visit www.uei.com, or contact info@uei.com. For more information about Sensory or its technologies, please visit www.sensory.com,or email sales@sensory.com.

 

 

About Sensory

Sensory Inc. creates a safer and superior UX through vision and voice technologies. Sensory’s technologies are widely deployedin consumer electronics applications including mobile phones, automotive, wearables, toys, IoT and various home electronics. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNaturallarge vocabulary natural language embedded speech recognition. Sensory’s technologies have shipped in over a billion units of leading consumer products. Visit Sensory at www.sensory.com

 

TrulyHandsfree is a trademark of Sensory Inc.

 

 

About Universal Electronics

Universal Electronics Inc. (NASDAQ:UEIC) Universal Electronics Inc. (NASDAQ: UEIC) is the worldwide leader in universal control and sensing technologies for the smart home. Its broad portfolio of patents includes QuickSet Cloud® service that utilizes the world’s most complete knowledge graph of devices to detect and interact with thousands of entertainment and smart home devices. The company designs, develops, and manufactures innovative products that are used by the world’s leading brands in the audio, video, subscription broadcasting, connected home, home energy management, and mobile device markets. UEI’s many first-to-market innovations have helped transform the home entertainment control, home security, and home energy management and sensing industries. More information is available at http://www.uei.comandquicksetcloud.com

###

 

All trademarks appearing herein are the property of their respective owners.

 

Nevo, QuickSet, and Ecolink are trademarks of Universal Electronics Inc.

 

Safe Harbor Statement

This press release contains forward-looking statements that are made pursuant tothe Safe-Harbor provisions of the Private Securities Litigation Reform Act of 1995. Words and expressions reflecting something other than historical fact are intended to identify forward-looking statements. These forward-looking statements involve a number of risks and uncertainties, including the timely development, delivery and market acceptance of UEI’s Nevo Butler product and associated service offerings, and other technologies identified in this release; the continued penetration and growth of the digital assistant products and consumer technologies identified in this release; and other factors described in the Company’s filings with the Securities and Exchange Commission. The actual results that the Company achieves may differ materially from any forward-lookingstatement due to such risks and uncertainties. The Company undertakes no obligations to revise or update any forward-looking statements in order toreflect events or circumstances that may arise after the date of this release.

Sensory Releases TrulySecure Face Authentication with 3D Camera Support, GPU Processing and Optional Cloud Capabilities

October 24, 2018

TrulySecure, Sensory’s class-leading face and voice ID solution found in top-selling smartphones and banking apps can now harness the benefits of 3D camera technology to authenticate users in all lighting conditions, even complete darkness

SANTA CLARA, Calif., – October 24, 2018 – Sensory, a leader in speech and vision technologies that enhance the user experience and security of consumer electronics, today announced the release of its fourth generation of TrulySecure™ FIDO Certified™ multimodal biometric authentication technology. Now smarter, faster and more secure than ever before, the TrulySecure 4.0 SDK boasts a variety of new AI features that cater to today’s smartphones, mobile apps, and IoT devices, including support for 3D cameras, GPU utilization for authentication processing, new liveness challenges and options for integrating components of TrulySecure into cloud-based authentication systems.

TrulySecure’s AI Gets Smarter

With each subsequent revision, Sensory continues to significantly enhance the performance, security and features offered by TrulySecure. Version 4.0 continues the trend by expanding on Sensory’s market-proven face authentication AI performance and accuracy. With version 4.0, TrulySecure’s deep learning AI has been trained on a data set that is an order of magnitude larger than the previous generation, which has improved 2D facial recognition accuracy more than 50-percent.

TrulySecure Now Supports 3D and IR Cameras

A common problem with traditional 2D facial recognition solutions is the inability to authenticate users in challenging lighting or no-light scenarios. The use of an IR illuminator completely eliminates this problem, essentially allowing TrulySecure to see clearly and authenticate users in all lighting conditions, including complete darkness.

3D camera support also increases the robustness of TrulySecure to varying pose angles, making the system more accurate during casual use across a broader range of conditions, and more resistant to spoof attacks.

TrulySecure’s support of 3D camera data has been developed in collaboration with pmd Technologies from Germany, the worldwide leading 3D Time-of-Flight CMOS-based digital imaging technology supplier. 3D cameras from pmd are already integrated into smartphones, robots, cars and AR headsets.

Click here for a short video that outlines the benefits of 3D/IR cameras.

GPU Utilization for Faster Authentication

Another major update in TrulySecure is the ability to split the biometric authentication data processing load between a device’s GPU and applications processor. To accomplish this, key processor-heavy components of the core TrulySecure algorithm were isolated, streamlined and specially ported to run on a GPU. In testing, it was found that those isolated components of TrulySecure run as fast or even faster on the GPU than on the AP. Moving heavy processing components of TrulySecure from the AP to the GPU allows the applications processor to either prioritize other tasks, or work in parallel with the GPU to cut the amount of processing time required for the TrulySecure algorithm in half.

As an added bonus, isolating and streamlining processor-heavy components of the TrulySecure algorithm has opened up a whole new realm of possibilities for porting to other embedded environments in the future.

Unrivaled Anti-Spoofing and Liveness Detection

An area of concern for all authentication modalities is spoofing. While previous generations of TrulySecure face and voice recognition featured industry-leading anti-spoofing and liveness detection capabilities, TrulySecure 4.0 makes spoofing a concern of the past. The first major leap forward from the previous version of TrulySecure is the use of 3D image data for authentication. This allows TrulySecure to not only recognize the user’s face, but the shape and contour of it too – and immediately reject 2D images and videos of the user’s face. Requiring 3D facial imagery serves as an excellent anti-spoofing measure, but not all devices have 3D cameras. For traditional 2D RGB camera applications, Sensory’s TrulySecure now features a face liveness challenge that makes it virtually impossible for anybody but the enrolled user to get in. TrulySecure’s face liveness challenge requires the enrolled user to follow prompts telling them what kind of movement to make in order to be authenticated. Additionally, TrulySecure now features an ‘eyes open’ challenge, that requires the user’s eyes to be open during authentication.

TrulySecure Adds Greater Support for Cloud-Based Authentication

Sensory’s technologies have long been the go-to for those looking to integrate powerful AI at the edge, but now TrulySecure can make cloud-based authentication technologies faster, more convenient and more secure.

One way that TrulySecure can do this is via its incredibly quick on-device enrollment component for federated authentication. With federated authentication, once a user completes the TrulySecure enrollment process on their device, TrulySecure creates a user enrollment template that can be handed off to the authentication server. Once the template is received by the server, it can be sent to other devices as needed, allowing the enrolled user to authenticate by face on any permitted device or app.

TrulySecure can also be used to reduce authentication data loads sent to cloud-based authentication systems by moving pre-authentication steps like liveness detection and feature extraction to the edge. TrulySecure’s on-device liveness detection can be used to immediately verify user authentication samples for liveness before sending captured authentication images to the server for processing. Taking it another step further, by enabling TrulySecure’s on-device feature extraction, once the AI detects liveness, it can then immediately convert the user’s facial features into templates (irreversible mathematical data) that can be sent to the authentication server instead of sending multiple images. This mitigates security risks associated with sending photos of a user’s face used for authentication over the internet, and significantly reduces the amount of data sent to the cloud for authentication.

Ideal for a wide range of applications, including smartphones, tablets, PCs, personal assistant technologies and robots, Sensory’s SDK for TrulySecure 4.0 face authentication is now available and currently supports ToF 3D cameras from pmd Technologies.

For more information about this announcement, Sensory or its technologies, please contact sales@sensory.com ; Press inquiries: press@sensory.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 TrulyHandsfree™ 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.

Sensory Makes Wake Words Smarter with New High-Res Voice Recognition and Authentication

September 27, 2018

Sensory, the leader and originator of wake words for personal assistants, raises the performance bar for always-listening wake word and speech recognition, with upgraded turn-key voice interface solutions for devices of all shapes, sizes and power requirements

Santa Clara, Calif., September 27, 2018 – Sensory, a Silicon Valley-based company focused on improving the user experience and security of consumer electronics through state-of-the-art embedded AI technologies, today announced that it has made significant upgrades to the embedded AI in its sixth generation of TrulyHandsfree™, boosting the technology’s already industry-leading wake word performance and accuracy by more than 65 percent. Additionally, TrulyHandsfree boasts improved deep-neural network training that allows for even better near- and far-field speech recognition performance in all room conditions.

“In ideal conditions, an always-listening wake word recognizer should only wake the voice UI when it hears the wake word, and never false fire,” said Todd Mozer, CEO of Sensory. “This is how we designed TrulyHandsfree to operate, and with the upgraded AI technologies in version 6.0, it works exactly as it should even in far less than ideal conditions. TrulyHandsfree has long been the performance benchmark that other voice UI solutions strive to match. With our sixth generation, the bar for efficiency, security, wake word accuracy, and near- and far-field performance has been set much higher, making it the ideal wake word solution for any kind of voice-enabled product design.”

Greater Wake Word and Speech Recognition Accuracy

Version 6.0 improves performance and word recognition accuracy relative to the last two generations of TrulyHandsfree by reducing wake word false positives by more than 65%. This reduction is due to Sensory’s new high-resolution speech feature front-end that sees a higher resolution digitized representation of the speech audio, combined with the introduction of on-device wake word post-qualification. Post qualification uses intelligence about wake word events to better discriminate against false positives. In addition to enhanced wake word performance, Sensory’s new high-resolution speech feature front-end has improved upon what was already the benchmark for embedded speech recognizers and contributed a significant boost in TrulyHandsfree 6.0’s speech recognition performance and accuracy over previous generations. Sensory’s new high-resolution speech feature front-end enhancements in accuracy also enable TrulyHandsfree to support multiple wake words, like “Okay Google” “Alexa™,” “Hey Cortana,” “Hey Siri” and ““Xiaodu, Xiaodu” in a single implementation with great performance. This allows device makers to create new products with a user-friendly voice interface that works with more than one digital assistant technology.

Tolerance of Accents, Dialects and Varying Room Conditions

Sensory upgraded the machine learning within TrulyHandsfree to take advantage of high-resolution audio information for deep-neural net training. This improved training allows the algorithms to anticipate a variety of factors associated with wake word performance, including understanding how one person, or a population of people, may pronounce a wake word. It also takes into consideration acoustic challenges like various room configurations, device placement, room size, reverb and echo. This ensures superior always-listening speech recognition performance regardless of where the device is placed in a room.

Enhanced Security Makes Sure That It’s You Speaking

Some of the most notable challenges facing the IoT industry is privacy and data security. TrulyHandsfree 6.0 does all processing on device, keeping voice data completely safe by never storing it or sending it to the cloud. Additionally, TrulyHandsfree 6.0 includes a layer of voice biometrics recognition in the voice interface for user authentication and security. TrulyHandsfree’s embedded high-resolution voice enrollment and speaker verification (SV) technology is flexible, allowing users to enroll their voice and their own custom wake word or passphrase, restricting unauthorized users from accessing the voice user interface. Even if an unauthorized person learns the custom wake word or passphrase, Sensory’s voice biometrics technology will recognize that it’s not the enrolled user speaking and not authenticate them.

Improved Barge-in and Far-Field Performance

Specifically tuned to provide an ideal voice barge-in experience with TrulyHandsfree, Sensory offers upgraded AEC solution that supports single mic input systems with mono or stereo sound sources. This technology allows users to interrupt their devices by saying the wake word while the device is in the middle of playing voice prompts, music or other sounds, at any volume level. Sensory’s new high-resolution speech feature front-end and AEC also play major roles in making TrulyHandsfree better at hearing users in a variety of room sizes and configurations, making TrulyHandsfree 6.0’s far-field wake word performance second to none.

High-Resolution Speech Recognition, Same Efficient Footprint

In addition to being more accurate, TrulyHandsfree 6.0’s new high-resolution speech feature models are scalable and extremely efficient. Its wake word, command and control, SV and AEC all feature a compact footprint, and work with a wide range of low power DSP to high-power applications processors. TrulyHandsfree’s AEC technology is also scalable and can be tuned to optimally balance acoustic echo cancellation performance requirements and MIPS/power restrictions. For ultra-low power devices that have limited battery capacity such as wearables, Sensory offers its Low Power Sound Detector (LPSD) hardware component for DSPs and smart microphones. LPSD reduces low-power configurations of TrulyHandsfree wake words to operate at an average battery draw of under 1mA.

TrulyHandsfree is the most widely deployed embedded speech recognition engine in the world, having enabled a hands-free voice user experience on more than 2 billion devices from leading brands worldwide. TrulyHandsfree offers support for every voice UI application with several types of wake word options, such as independent fixed wake words, user enrolled fixed wake words, and user defined wake words. Sensory offers off-the-shelf wake word models for all major IoT cloud services, including Amazon AVS, Apple Siri, the Google Assistant and Microsoft Cortana, as well as wake word models for third-party devices that support cloud AI systems from Baidu, Alibaba or Tencent. Sensory can also combine multiple wake words into one solution.

Sensory’s TrulyHandsfree supports US English, UK English, Arabic, Dutch, French, German, Italian, Japanese, Korean, Mandarin, Portuguese, Russian, Spanish, Swedish and Turkish. The TrulyHandsfree SDK is available for Android, iOS, Linux, QNX and Windows. Sensory provides developer support for cloud service interfaces on Linux, Android, iOS and Windows as well as support for dozens of proprietary DSPs, microcontrollers, smart microphones and other low-power embedded devices.

Additionally, ultra-low-power deeply embedded ports of TrulyHandsfree are available for leading DSP/MCU IP cores from ARM, Cadence, CEVA, NXP, Synopsys and Verisilicon, as well as for integrated circuits from Ambiq Micro, Analog Devices, Cirrus Logic, DSP Group, Fortemedia, Intel, Knowles, Microchip (Microsemi), NXP, Qualcomm, QuickLogic, Realtek, Synaptics, STMicroelectronics, TI, Yamaha, and XMOS.

For more information about this announcement, Sensory or its technologies, please contact sales@sensory.com; Press inquiries: press@sensory.com.

# # #

About Sensory
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. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNatural large vocabulary natural language embedded speech recognition. Sensory’s technologies have shipped in over a billion units of leading consumer products. 

TrulyHandsfree is a trademark of Sensory Inc.

TrulySecure Biometric ID Now in Two Dozen Banking Apps from Major World Banks

June 27, 2018

Sensory’s TrulySecure Provides Instant, High-Security On-Device Face and Voice Biometric Authentication

 

Santa Clara, Calif., June 27, 2018Sensory, the leader in on-device AI technology, today announces that its TrulySecure™ face and voice biometric fusion technology has quickly become the de facto standard for providing seamless, high-security biometric authentication on mobile applications from global banks and financial institutions. Now in two dozen bank apps, TrulySecure is a FIDO-certified face and voice biometric recognition solution that provides cross platform, extremely secure & convenient, on-device authentication without requiring any specialized sensors.

 

Sensory has established numerous partnerships with notable technology integrators for the banking and enterprise sector, including EZMCOM, Fujitsu, Samsung SDS and VeriTran. Through these relationships Sensory has enhanced the user security and user experience of mobile banking apps provided by leading banks such as Alior, AXIS, Banorte, ICICI, Maybank, Mizuho Bank, Qatar Islamic Bank and numerous others. Additionally, Sensory has established partnerships with decentralized authentication solution providers like HYPR, Nok Nok and others to offer TrulySecure’s face and voice authenticators as components of their multi-factor authentication systems.

 

“Since announcing the first version of TrulySecure, we have had a great deal of interest from banks wanting to utilize our technology for adding greater user security to their apps without compromising convenience. While we are certainly excited to have more than two dozen banking customers, we believe that we are just now beginning to see the tipping point for mass adoption among banks globally. We look forward to continuing our leadership role in the biometric revolution taking place in the banking market by constantly improving TrulySecure and working even more closely with our partners to deploy it,” said Todd Mozer, CEO of Sensory.

 

TrulySecure delivers multiple advantages over other biometric solutions including:

  • Deployable on the widest variety of new and existing devices (no special sensors required)
  • Supports 2D, 3D and IR cameras
  • Simple UI – no tapping screens, swiping fingers, or carefully positioning an eye
  • Fast enrollment and usage
  • Robustness to environments with poor lighting or high noise
  • Anti-spoofing techniques such as motion and skin texture analysis
  • Multi-biometric fusion to enable smart adaptation to environments
  • FIDO (Fast Identification Online) UAF Certified

 

Ideal for a wide range of applications, including banking, enterprise, mobile payment, password manager and retail apps, TrulySecure has SDKs and FIDO-compliant authentication solutions for both Android and iOS, allowing developers to offer the same elegant user authentication experience across nearly all of today’s mobile devices. Sensory offers a streamlined reference UI for customers to use as-is or modify for use within their own Android and iOS apps. Additionally, Android and iOS applications can take advantage of the added layer of security offered by Android KeyStore and iOS Keychain encryption to further protect the biometric data while not in use by the system.

 

In addition to providing ultra-secure biometric authentication solutions for mobile banking apps, Sensory continues to innovate exciting new technologies designed to enhance the overall user experience they offer. Sensory’s new virtual bank teller demo is a proof-of-concept application for Sensory’s advanced embedded artificial intelligence (AI) technologies working together to provide bank and financial institution customers a lifelike bank teller experience directly on their smartphones and tablets, without the need and risk of sending valuable information to the cloud.

 

Watch the virtual bank teller demo here: https://youtu.be/vBh337eqzpA.

 

For more information about this announcement, Sensory or its technologies, please contact sales@sensory.com;Press inquiries: press@sensory.com.

Sensory Adds Suite of New Biometric Voice Features to TrulySecure Speaker Verification

May 23, 2018

Sensory’s TrulySecure 2.0 now includes wake word support, text independent speaker ID, seamlessly enrollment and major accuracy improvements

Santa Clara, Calif., May 23, 2018 – Sensory, a Silicon Valley-based company focused on improving the user experience and security of consumer electronics through state-of-the-art embedded AI technologies, today announces the next-generation of its low-resource, noise-robust, TrulySecure Speaker Verification (TSSV) SDK. TSSV 2.0 boasts a variety of new embedded voice biometric authentication features and accuracy improvements.

“Sensory’s TrulySecure line of patented face and voice biometrics are a huge market success having been designed into leading banking applications, and mobile phones from leaders like Samsung, LG, and Motorola. We believe TrulySecure Speaker Verification 2.0 has a lot of market potential, especially with the addition of new security features, text independence, anti-spoof approaches and much more,” said Todd Mozer, CEO of Sensory.

TSSV 2.0 is a modular biometric software component providing speaker verification and identification. These biometric features run embedded and can be added to any on-device for profile switching, access security, and tracking conversations with personal assistants based on who is speaking. At its core, TSSV encapsulates novel advances in front-end noise suppression, robust feature extraction, as well as spectral and temporal speaker modeling to offer extremely accurate and secure voice biometric enrollment and authentication of users, even in noisy environments. The technology enables maximum privacy protections by running on-device and it supports multiple users with adaptation, allowing it to become more accurate and secure over time. TSSV can also be fused with Sensory’s face biometrics, allowing for quick and seamless recognition and authentication of users via face or voice (convenience mode), or can be configured to require both face and voice confirmation for greater user security (TrulySecure mode).

TSSV provides device makers and app developers the flexibility to enable voice biometric security in three different modes, text independent, text dependent fixed passphrase and text dependent user-defined passphrase.

  • Text Independent: A new feature for TSSV 2.0, this method models the user’s voice across any speaking situation and identifies users regardless of what they say, with no passphrase required.
  • Text Dependent Fixed Passphrase: This method uses a predefined passphrase and can work in parallel with popular wake words like “Alexa,” “Hey Siri,” and others, allowing users to be instantly identified when they say the wake word.
  • Text Dependent User-Defined Passphrase: This method allows users to enroll their own custom passphrase for authentication, adding extra security against intruders who don’t know the custom passphrase

New Features and Improvements for TSSV 2.0

  • Accuracy Improvements – improvements in feature extraction, reverb modeling, noise robustness/SNR have led to a decrease in equal error rates (EER) of more than 25% from TSSV 1.0.
  • Wake word functionality – Now TSSV has built in wake word capability for OS based systems. Wake-word creation is automated and fast once appropriate data is collected.
  • Text Independent Speaker Verification – Now users can be tracked seamlessly by their voice without specific passphrase requirements.
  • Seamless Enrollment – No longer is a compliant user training required to build voice models. Devices can with TSSV 2.0 can now listen to usage and build and adapt models without formal training. Click Here for Seamless Enrollment Demo Video
  • Voice Liveness – Prevents spoof attacks by presenting an interactive challenge sequence that must be performed to verify that the input is from an actual user and not a recording.
  • Improved SDK – Documentation significantly expanded and improved. The SDK provides numerous code examples and now offers support for Python.

Sensory’s TrulySecure Speaker Verification supports all languages and dialects. The TSSV 2.0 SDK is available now through Sensory at a cost of $2,500, which includes up to five hours of support. An SDK for TSSV is available for Android, iOS, Linux, Mac OS, Tizen and Windows implementations.

For more information about this announcement, Sensory or its technologies, please contact sales@sensory.com; Press inquiries: press@sensory.com.

About Sensory
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. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNatural large vocabulary natural language embedded speech recognition. Sensory’s technologies have shipped in over a billion units of leading consumer products.

TrulySecure is a trademark of Sensory Inc.

« Older Entries