Core Technologies
Core Technologies
The most powerful, most intelligent AI assistant solutions for global mobility, Cerence offers a robust portfolio of products, services, toolkits, and innovations that brings tomorrow’s user experience to today’s mobility ecosystem.
As the car of the future takes hold, Cerence leads the way with a new era of in-car assistants: a multi-modal, deeply integrated, proactive companion that accompanies drivers throughout their daily journeys, delivering effortless interaction that keeps drivers safe, comfortable, productive, and informed.
Cerence Co-Pilot
Cerence Co-Pilot is a first-of-its kind, multi-modal driving experience that transforms the automotive voice assistant into a proactive, intuitive, AI-powered companion that can support drivers like never before. Cerence Co-Pilot runs directly on a vehicle’s headunit, with advanced AI deeply integrated with car sensors and data to understand complex situations both inside the vehicle and around it. Serving as the central brain of the car, it analyzes a combination of voice, gaze, gesture, and touch input and information from the car’s sensors while flexibly and securely integrating edge technologies with cloud services to make driving more intuitive, connected, and enjoyable.
At the core of Cerence Co-Pilot is proactive AI, a series of new innovations that use real-time data, built-in intelligence, user preferences, and vehicle sensor information to keep drivers informed and offer to perform actions on their behalf – before they even need to ask – protecting both driver and vehicle.
Cerence Drive
Developed in close partnership with OEMs all over the world, Cerence Drive supports your distinct vision with an open platform that enables the look, feel, functions, configurability, content choices, and UX to be completely customized, elevating and adapting seamlessly to your brand. With a singular, unified AI stack that includes the best of Cerence’s embedded and cloud technologies, Cerence Drive offers rapid functionality, uninterrupted connectivity, and elegant integration. It also boasts the industry’s most natural, intuitive interactions, using state-of-the-art AI to become continuously more human.
Cerence Drive understands individual preferences, personalizes entertainment, and executes complex, contextual commands. It can also find preferred parking, play users’ favorite songs, direct them to the gas stations with the best prices, and prioritize the voices it needs to hear while muting the ones it doesn’t, maximizing the safety, productivity, and enjoyment of every customer journey.
Conversational AI
A truly intelligent mobility assistant makes every interaction better, leaving your customers safer, more productive, and happier behind the wheel. But only those equipped with Cerence Drive’s conversational AI will be intuitive enough to truly understand their users, going beyond speech recognition to the depths of true understanding and comprehension. With natural language understanding and unmatched levels of voice recognition accuracy and performance, drivers can speak as their most natural selves – no more learning specific commands or entering an address in a prescribed, specific way. Say “I’m cold,” and we’ll know to turn up the heat; say “Navigate to the Empire State building,” and we’ll start the route.
Equipped with broad domain coverage, access to external content services, and interoperability with third-party assistants, Cerence helps voice assistants go beyond simple commands to address even the most complex, multifaceted requests. Its understanding of context encompasses multiple sources and established history, allowing it to act on input like, “Find a good coffee shop with Wi-Fi en route, about two hours from the hotel—and make sure I turned the living room thermostat to 50.”
Human-Like Voice Output
As the use of in-car voice assistants explodes, they have become an innovative point of differentiation. Mobility OEMs are looking for solutions that can deliver the most natural and human-like voice output quality, unlocking new use cases for their users.
With Cerence Reader, our neural net-based text-to-speech (TTS) technology, we’re bringing a stunningly human-like virtual personality into the car, delivering the voice output quality that drivers expect in the expanding world of virtual assistants.
Cerence Reader leverages advances in AI and processing hardware to bring unprecedented levels of natural speech to the car. Nearly indistinguishable from a human voice, Cerence Reader can change its speaking style and emotional tone based on content and context. It even features long-form reading capabilities, including natural pausing and breathing and varying tonalities based on content, including current events, sports, or documentary-style pieces.
Deep Content & Capabilities
Cerence Drive Domains are like apps or skills – packaged solutions that provide a rich, intelligent mobility assistant experience as the content and capability engine for the voice assistant.
Built with the automotive and mobility user top of mind, Cerence Drive Domains power everything you need for an intuitive, natural experience. That means innovative ASR and NLU technologies and integrations with leading content providers. A hybrid solution available on cloud and embedded platforms in over 30 languages.
With Cerence Drive Domains, the automotive assistant is ready to give directions, entertain, send messages, control in-vehicle functions, keep drivers connected and safe, and much more.
Coexistence & Interoperability
In today’s ever-expanding world of virtual assistants, coexistence and interoperability is key. We firmly believe that the car should be a center for interaction with all the varying assistants, content and services a driver interacts with each day – not a separate technological island.
Cerence Cognitive Arbitrator makes the dream of virtual assistant coexistence a reality, delivering seamless, integrated access to the vast array of assistants and content in a singular, voice-activated interface – all without compromising the privacy, security, or integrity of automakers’ uniquely branded user experience.
Cerence Cognitive Arbitrator turns every car into an intelligent hub, integrating third-party intelligence with automakers’ in-vehicle systems to create a connected ecosystem controlled by the OEM. It puts the automotive assistant at the center, processing each request through the assistant or service best suited to complete the task – from consumer-oriented voice assistants, like Amazon Alexa or Apple Siri, to in-home entertainment devices, banking assistants, and meal delivery apps – without deviating from the core user experience.
In-Car Communications
The car can be a noisy place. From the sounds of the road to competing entertainment and chatty co-pilots, extra noise can interfere with not just the automotive assistant, but even conversations between the driver and passengers. Passengers shout; drivers turn around to speak to passengers in the back, all increasing distraction and compromising safety on the road.
Enter Cerence In-Car Communication (ICC). Part of the Cerence Audio AI suite, ICC improves the speech quality and intelligibility of in-car conversations between the driver and passengers through an intercom system. Perfectly suited for larger vehicles like minibuses and vans where there are more than two rows of seats, ICC picks up speech from the driver through specially placed microphones, processes and cleans it up, and plays it over the speakers in the rear of the car – all in an instant.
Speech Signal Enhancement
In order to be understood, we must first be heard. That’s why Cerence Speech Signal Enhancement (SSE), part of the Cerence Audio AI suite, is a critical piece of our platform. SSE is a suite of sound processing technologies that remove noise from microphone inputs, teeing up our world-class voice recognition and natural language understanding engines to work their magic with crystal-clear input from drivers and passengers.
SSE is critical to the in-car experience, enhancing speech quality for phone calls, enabling drivers to effectively use wake-up words and seamlessly interrupt and interact with the assistant, and allowing us to create speaking zones so the assistant knows exactly who is speaking – and who might need to be muted. In the future, SSE will be even more critical. Imagine a shared, autonomous vehicle with multiple passengers on board. SSE will allow individual passengers to interact with the vehicle without confusion or interruption.
Multi-Zone Intelligence
Part of the Cerence Audio AI suite and leveraged alongside Speech Signal Enhancement, our multi-seat intelligence technology enables everyone in the car to interact with the automotive assistant, without worry of interference or interruption. Deep neural net-based noise reduction with superior noise suppression supports a new level of multi-zone, hands-free communication, with up to eight zones with a maximum of 30 microphones. It’s also equipped with up to 16 configurable output channels with flexible zone selection and multi-zone arbitration to support both the Cerence assistant and multiple third-party assistants.
Beyond interaction with the automotive assistant, multi-seat intelligence delivers an ideal solution for drivers taking phone calls on the road, enabling perfect suppression of interfering speech from other zones by combining beamforming with passenger interfering techniques. Pair that with the ability to enable and disable zones dynamically during a conference call, and you’ve got an entirely new in-car phone calling experience.
Natural Voice Assistant Activation
Push-to-talk buttons and wake words have long been the standard ways that users begin their conversations with their assistants. But what if your assistant simply knew you were talking to it – no button or “hey” required?
Enter Cerence Just Talk, revolutionary, AI-powered technology from Cerence that has the smarts to detect when drivers are talking to the assistant, and to keep quiet when they’re not. With Just Talk, drivers can simply begin speaking when they have a question or command for the assistant. They don’t need to push a button or say “Hey {insert favorite car brand}.” The system knows when it’s being summoned based on the words uttered, how the user spoke them, and the context of the conversation, delivering a more intuitive, human-like experience in the car.
