VOCALZOOM

Multifunction Sensors Enable New Generation of Human-to-Machine Communication (HMC) Fueling The Speech-Activated Digital Lifestyle: VocalZoom Enables More Natural, Personalized and Secure Voice-Control Experience VocalZoom helps solve one of the biggest challenges facing the move beyond keyboards and touchscreens to a significantly improved user experience (UX) for today’s increasingly mobile and interconnected world. The problem? While voice control user interface (UI) solutions ha... ve been heralded as the next step, they can’t make devices do as they’re asked without exceeding the threshold of user frustration. They don’t capture human speech in such a way that a person’s voice can be seamlessly, naturally and conveniently used for everything from controlling virtual assistants, wearable devices and car functions to authenticating individuals for such personalized actions as opening locked doors, transacting, and performing other secure tasks. Today’s solutions need more and better voice data. The company’s multifunction HMC sensor technology can help. The Challenge With human-to-human voice interactions, the goal is to optimize how conversation sounds. In contrast, the key for human-to-machine interactions using virtual assistants and automotive voice control is whether the machine did what it was told to do, quickly and accurately enough to satisfy the user. Today’s technologies aren’t up to the task. Voice processing can improve audio’s overall quality (generally to industry-standard profiles that have been deemed most pleasing to the human ear), but has difficulty with transient or loud sounds typical of real life, such as when a person is surrounded by street noise. And although noise reduction algorithms used with acoustic microphones have improved, today’s microphones can’t be implemented with enough directional acquisition capabilities to isolate one voice from others, especially in noisy environments. Human-to-machine interactions demand more precisely targeted voice acquisition, at any noise level, than today’s microphones provide, so machines can identify users, understand their commands and correctly respond to and obey the person authorized to give them instructions. Achieving a critical combination of authenticated and accurate voice control requires going beyond a simple human-to-machine interface (HMI) to the next-generation, higher-order concept of secure human-to-machine communication (HMC). Solving the Problem The VocalZoom multifunction HMC sensor adds an important new UX layer: enabling systems to gather critical additional information exclusively about the user who is communicating with a device. This information is derived from the optical data generated during speech as facial skin (around such areas as the mouth, lip, cheek and throat) vibrates. By focusing the VocalZoom HMC sensor on these areas, measuring the vibrations, and converting this data to an audio signal, the speaker’s voice can be isolated, giving voice authentication and control platforms a near-perfect reference signal with which to operate – regardless of noise levels. VocalZoom’s solution will become increasingly important to 1) support growing use of wearables, in-car infotainment systems and other applications where voice control delivers the best, most natural (not requiring looking at or touching) UX, and 2) meet the increasingly important need to employ voice as an authentication factor for an expanding range of personalized on-line and mobile financial, healthcare and other secure cloud-based services. The sensor can also be used to enhance general voice communication and for applications including proximity sensing, vibration measurement and 3D imaging, creating a new category of multifunction HMC sensors for many simultaneous, high-value UX-focused system capabilities. Compact and power-efficient, the sensor fits into small devices and is available for both head-mounted (virtual and augmented reality glasses, headsets, helmets) and remote (voice-controlled automotive infotainment and self-service kiosks) applications. Applications Better Performing, More Power-Efficient and Streamlined Headsets and Other Wearables VocalZoom is redefining head-mounted communication devices in applications from aviation headphones to gaming and virtual/augmented reality gear to emergency response communications solutions. The performance, size and power efficiency of the multifunction HMC sensor enable system designers to “remove the boom” that was previously required in order to position an acoustic mic close to the user’s voice in a challenging noise environment, cutting costs while improving the user experience. The Most Convenient Form of Access Control The VocalZoom multifunction HMC sensor provides a single solution for adding voice authentication to voice control solutions. It delivers a near-perfect isolated signal, becoming the eyes and ears of solutions that can both understand and identify users and ensure they are who they claim to be. Truly “No-Hands” and Distraction-Free Automotive Voice Control Automotive industry experts from J.D. Powers to the AAA Foundation have concluded that “hands-free” does not yet mean risk-free. VocalZoom solves this problem with a solution that provides seamless, near-perfect performance in noisy environments. A single VocalZoom multifunction HMC sensor can be installed in the rear-view mirror and used to authenticate the driver, provide clean, driver-isolated voice commands and potentially deliver additional driver-monitoring capabilities to improve user safety and convenience.