What made Cerence's highlight at the exhibition was its demonstration of how to combine voice recognition and head tracking technology to achieve in-car control functions.
When the cabin buttons become sounds, sights, gestures or even emotions, will you love your car more?
Cerence calls this new interaction mode "a humanized, multi-sensory, multi-modal interaction experience". The company also brought a new high-end solution based on the Cerence Drive platform to the 2020 CES, directly targeting the buttonless interaction experience, and called out the slogan of "creating the most natural and humanized in-vehicle experience to date".
Sanjay Dhawan, CEO of the company, said: "We believe that the most engaging in-car experience is one that is as close to human interaction as possible: a multi-sensory, conversational experience that includes full interaction through voice, eye movement and gesture. The innovations we are demonstrating at CES, especially gesture-based interactions, are designed to enhance the in-car experience and create a safe, efficient and enjoyable environment - which is at the core of the in-car experience of today, L3 and above autonomous vehicles and the future."
What made Cerence's highlight at the exhibition was its demonstration of how to combine voice recognition and head tracking technology to achieve in-car control functions.
In addition to multimodal interactions that combine driver and passenger gaze with voice recognition, live demonstrations included: intelligent voice traffic notifications, natural language output to help drivers choose driving routes, the new Cerence EVD emergency vehicle detection, the debut of the Cerence Car Life solution suite, and gesture-based interactions through the windshield user interface.
e.GO Mover self-driving electric bus
All of these cutting-edge technologies are concentrated on a revolutionary self-driving electric bus called "e.GO Mover".
The car focuses on the user experience of future autonomous driving, electric and shared cars, and combines multiple core technologies from Cerence and Saint-Gobain Sekurit. Specifically:
Multilingual Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU): Enables passengers and people outside the vehicle to interact with the car in a conversational manner in their native language.
Text-to-speech (TTS) and natural language response: Enable this car to have fluent, human-like communication with passengers and people outside the car, and emotional TTS can enable the car to change the way it speaks based on content and context.
Speech Signal Enhancement (SSE): Shields the microphone input from noise and distinguishes between different vocal regions, making it possible to identify only one speaker’s voice – critical for ride-sharing use cases and for interacting with the bus externally.
Transparent screen technology: enables information to be projected inside and outside the vehicle.
Unlike many industry insiders who argue that "the interaction of self-driving cars will be led by smartphones," Cerence believes that multimodal, multi-language interactive experiences are far superior to smartphones in building user trust and confidence, and have the opportunity to accelerate consumers' acceptance and use of self-driving cars.
In fact, there are more factors that affect consumer market confidence than this. Safety is always the biggest challenge facing self-driving cars.
Therefore, Cerence also launched Emergency Vehicle Detection at the same time, introducing driving safety protection functions to Cerence Drive. When an emergency vehicle is approaching, the in-vehicle assistant integrated with Cerence EVD function will proactively remind the driver so that they can make corresponding driving adjustments. Because acoustic echo cancellation technology can effectively eliminate music playback in the microphone signal, even if the song the driver is listening to contains the sirens of emergency vehicles or other sounds, the system can detect the sirens and issue notifications in time.
Cerence recently surveyed more than 1,500 U.S. consumers to understand how they use in-car features to search around them. When asked how future in-car technology could best improve their driving experience, nearly half (44%) of respondents said they would like to get more help in stressful driving situations.
Cerence DRIVE Labs also contributed a set of research data. They investigated drivers' expectations and opinions on the use of siren detection. It was found that drivers are very willing to pay for this innovative feature. 67% of respondents expect that once a siren is detected, the system will be able to immediately notify and lower the volume of all other audio in the car. These users said that siren detection will be the most valuable feature when they are in heavy traffic and in suburban/urban environments due to the influence of noisy sounds inside or outside the car. They also gave some feedback: they hope to know the relative position of the siren, including the direction of the emergency vehicle, and distance information.
Cerence Drive multi-modal interactive demonstration
Of course, strictly speaking, the above applications are just "tinkering" with the product itself. In order to subvert the traditional car model, Cerence makes full use of artificial intelligence technology and begins to seek breakthroughs in establishing an intimate relationship between drivers and cars among many solutions.
At the same time, the company announced the launch of Car Life, an artificial intelligence SaaS product suite that supports consumers to use voice to access smart car manuals, helping drivers interact with their cars and perform related operations. According to the official introduction, from the beginning of purchasing a car, users can get an upgraded user experience that supports new SaaS applications. Drivers only need to use voice and the in-vehicle infotainment touch screen to understand car information and access the artificial intelligence car manual, as well as make appointments for car maintenance and other services through the integrated dealer management system (DMS).
As cars become more complex, the user threshold is also rising subtly. There are too many functions in the car that need to be mastered, and a series of traditional operations such as notifications and warning lights are becoming more difficult. The SaaS application model of the suite supports customization for each car, specific car configuration, and gradually understands the driver's preferences, and provides information through supporting applications, car assistant voice, and in-vehicle infotainment system graphical display. Cerence Car Life will be included in the Cerence Drive solution and can be integrated with other global voice assistants such as Google, Amazon, Baidu, Alibaba, Yandex, etc.
Behind the product is the team’s own understanding of the future relationship between “people and cars”: “Like developing other long-term relationships, the relationship between drivers and cars is built on a deep understanding and appreciation of the car, from the first time they enter the car and throughout the entire life cycle of the car.” said Stefan Ortmanns, co-founder, executive vice president and general manager of core automotive business at Cerence.
From the perspective of commercial interests, for OEMs, if smart cars in the future can be closely connected with daily life and difficult to separate like electronic products such as smartphones, it will not only enhance the travel experience but also provide strong support for building brand loyalty.
Cerence ARK Demo
Of course, in addition to the sales end, automakers are more concerned about the production end.
For the Chinese market, Cerence has created the ARK turnkey voice AI solution, which provides rapid development, deployment and management of localized automotive voice assistants, attempting to significantly shorten the product development cycle.
Specifically, Cerence ARK integrates core voice assistant functions, including wake-up words, voiceprint verification, automatic speech recognition, natural language understanding, and text-to-speech, and has the advantages of openness, flexibility, and rapid deployment. It is the choice with the lowest investment cost, shortest development time, and best system performance. According to the official introduction, OEMs can create a personalized driving experience for customers, and through the system's built-in artificial intelligence learning capabilities, help drivers and passengers customize music, navigation, points of interest, news push, and other content access.
In the view of Kuai Wenrui, the company's founder and president in China, Cerence ARK is an innovative solution that subverts the automotive industry. Cheyunjun learned that the solution is now available in China and plans to release a global version in 2020. It provides three service levels - lightweight, standard and advanced, and comes with three key components - ARK Edge, ARK Client and ARK Cloud. Customers can flexibly choose components and deployment options.
Just looking at the ARK solution, it is clear that Cerence attaches great importance to the Chinese market.
The company just completed its split from Nuance Communications three months ago and became an independent Nasdaq-listed company. After its establishment, Cerence moved its R&D base, world-class design center, innovation center and UI laboratory in China to China. At the same time, out of consideration for localization needs, the company provides Chinese customers with a software development kit (SDK) to create customizable, out-of-the-box applications that can run on the Cerence Drive platform, and to provide OEMs and suppliers with overall solutions that only require a small amount of customization and can be delivered more quickly.
With the support of Nuance's 20 years of industry experience in the automotive business, Cerence has currently completed the deployment of nearly 325 million vehicles, including artificial intelligence travel voice assistants equipped by mainstream automakers such as Audi, BMW, Daimler, Toyota, Ford, Geely, SAIC, and GM.
Previous article:After electrification, smart cars will be the beginning of a nightmare for car companies
Next article:DAMO Academy once again won first place in authoritative autonomous driving evaluation, and the vehicle can identify "centimeter-level" obstacles
- Popular Resources
- Popular amplifiers
- A new chapter in Great Wall Motors R&D: solid-state battery technology leads the future
- Naxin Micro provides full-scenario GaN driver IC solutions
- Interpreting Huawei’s new solid-state battery patent, will it challenge CATL in 2030?
- Are pure electric/plug-in hybrid vehicles going crazy? A Chinese company has launched the world's first -40℃ dischargeable hybrid battery that is not afraid of cold
- How much do you know about intelligent driving domain control: low-end and mid-end models are accelerating their introduction, with integrated driving and parking solutions accounting for the majority
- Foresight Launches Six Advanced Stereo Sensor Suite to Revolutionize Industrial and Automotive 3D Perception
- OPTIMA launches new ORANGETOP QH6 lithium battery to adapt to extreme temperature conditions
- Allegro MicroSystems Introduces Advanced Magnetic and Inductive Position Sensing Solutions
- TDK launches second generation 6-axis IMU for automotive safety applications
- LED chemical incompatibility test to see which chemicals LEDs can be used with
- Application of ARM9 hardware coprocessor on WinCE embedded motherboard
- What are the key points for selecting rotor flowmeter?
- LM317 high power charger circuit
- A brief analysis of Embest's application and development of embedded medical devices
- Single-phase RC protection circuit
- stm32 PVD programmable voltage monitor
- Introduction and measurement of edge trigger and level trigger of 51 single chip microcomputer
- Improved design of Linux system software shell protection technology
- What to do if the ABB robot protection device stops
- Analysis of the information security mechanism of AUTOSAR, the automotive embedded software framework
- Brief Analysis of Automotive Ethernet Test Content and Test Methods
- How haptic technology can enhance driving safety
- Let’s talk about the “Three Musketeers” of radar in autonomous driving
- Why software-defined vehicles transform cars from tools into living spaces
- How Lucid is overtaking Tesla with smaller motors
- Wi-Fi 8 specification is on the way: 2.4/5/6GHz triple-band operation
- Wi-Fi 8 specification is on the way: 2.4/5/6GHz triple-band operation
- Vietnam's chip packaging and testing business is growing, and supply-side fragmentation is splitting the market
- Vietnam's chip packaging and testing business is growing, and supply-side fragmentation is splitting the market
- 【Home treasure】 esp32s2 freertos communication between tasks xQueue
- TI's Stereo Evaluation Module Reference Design for IV Sensing Audio Amplifier
- Share WB-MQTT Debug Assistant (Android mobile terminal)
- [TI star product limited time purchase] Bluetooth board arrives
- iTOP-4418 development board - Qt and minimal Linux system - extended root partition
- Ask a silly question
- Keeping an eye on all directions: A brief analysis of the development trend of TI's automotive surround view technology
- 【Project source code】 Altera DDR2 controller
- Many domestic chips now replace the STM series chips, which looks good in the short term. What do you think?
- High-speed circuit design practice