Xiaomi Mijia Smart Life New Product Launch Conference was held in Beijing. Three Xiaomi smart devices equipped with Horizon Robotics' self-developed Enhanced Speech Extraction (ESE) solution - Xiaomi Xiaoai Speaker PLAY, Xiaomi Xiaoai Speaker Universal Remote Control Panel and Xiaomi "Xiaoai Teacher" Pocket English Foreign Teacher - made their debut. After previously helping Xiaomi Xiaoai Touchscreen Speaker to create an intelligent voice front end, Horizon Robotics once again empowered multiple Xiaomi AIoT products to create a smooth and natural human-computer interaction experience.
In February this year, the Xiaomi Xiaoai touchscreen speaker equipped with Horizon's ESE solution was released and has been widely recognized by the market since its launch. For the Xiaoai speaker PLAY and Xiaoai speaker universal remote control panel released this time, Horizon further upgraded the ESE solution, significantly improving the wake-up rate under echo interference. At the same time, Horizon also maintained close cooperation with Xiaomi Brain to conduct fusion training on speech recognition technology (Automatic Speech Recognition, referred to as ASR), which greatly improved the accuracy of speech recognition.
Compared with the previous Xiaoai touchscreen speakers, Horizon has deeply optimized the Xiaoai Speaker PLAY and Xiaoai Speaker Universal Remote Control Panel released this time, reducing CPU and memory usage by 30%, significantly reducing power consumption. At the same time, considering the impact of wake-up rate and false alarm rate on user experience, Horizon R&D personnel also conducted in-depth analysis of the pronunciation characteristics, usage scenarios and noise types of wake-up words, and used the industry-leading deep neural network technology solution to optimize the system in a targeted manner. According to the project leader, the two Xiaomi Xiaoai speakers equipped with Horizon ESE solution released this time can be interrupted and woken up at any time in a complex noise environment, bringing users a smoother interactive experience.
At the press conference, Xiaomi's "Xiao Ai Teacher", a pocket English teacher that uses Horizon's ESE solution, was also unveiled as one of the blockbuster products of the event. "Xiao Ai Teacher" is not only an AI translator, AI oral training machine, AI voice recorder, AI repeater, but also an AI electronic dictionary and AI word memorization machine. Unlike the Xiao Ai speaker, "Xiao Ai Teacher" controls the start and end of sound pickup by buttons, and does not pick up sound continuously, which poses a challenge to the fast tracking of the algorithm. In response to this, Horizon has specially optimized the ESE solution, adding an adaptive equalization mechanism to adapt the recognition model. At the same time, by optimizing the front-end algorithm, voice noise reduction is effectively achieved, so that the voice recognition rate of Xiaomi's "Xiao Ai Teacher" remains at a relatively high level in the industry.
Regarding this cooperation, Yu Kai, founder and CEO of Horizon Robotics, said: "I am very happy to work with Xiaomi again to create heavyweight products for AIoT. AI on Horizon - being the most basic enabler in the AI era is Horizon Robotics' strategic choice. In the future, Horizon Robotics will give full play to its underlying core technology advantages and continue to provide the industry with ultra-high cost-effective AI chips, extreme power efficiency, open tool chains, rich algorithm model examples and comprehensive enabling services, and continue to achieve customer success through full open empowerment."
At present, Horizon can provide a full-link solution in the field of voice, including front-end signal processing, wake-up, voice recognition, semantic understanding and voice synthesis. The solution adopts the latest deep learning algorithm, and through the effective combination of "end" and "cloud", it can better solve the problem of voice recognition in complex scenarios. In the field of intelligent driving, Horizon can also provide full-vehicle audio solutions, including in-vehicle noise reduction, recognition, multi-mode interaction, partitioned sound pickup, partitioned playback and enhanced in-vehicle communication. In addition, Horizon's voice solution can not only support ARM platforms, but also provide strong support for low-power DSP platforms.
Not long ago, Horizon Robotics announced its corporate strategy of "AI on Horizon, Journey Together" for the first time, which is to be the most basic enabler in the era of artificial intelligence, and to achieve success for customers through chip open empowerment. Based on this strategy, Horizon Robotics has enabled multiple partners in the fields of intelligent driving and AIoT based on its self-developed AI chips and algorithms. In the future, Horizon Robotics will continue to focus on the construction and polishing of the basic technology platform composed of edge AI chips + tool chains, and help customers create more and more amazing intelligent terminal products.
Previous article:Google is reportedly moving some hardware production out of China
Next article:NXP Launches EdgeVerse Solution Platform to Accelerate Edge Computing
- Popular Resources
- Popular amplifiers
- e-Network Community and NXP launch Smart Space Building Automation Challenge
- The Internet of Things helps electric vehicle charging facilities move into the future
- Nordic Semiconductor Launches nRF54L15, nRF54L10 and nRF54L05 Next Generation Wireless SoCs
- Face detection based on camera capture video in OPENCV - Mir NXP i.MX93 development board
- The UK tests drones equipped with nervous systems: no need to frequently land for inspection
- The power of ultra-wideband: reshaping the automotive, mobile and industrial IoT experience
- STMicroelectronics launches highly adaptable and easy-to-connect dual-radio IoT module for metering and asset tracking applications
- This year, the number of IoT connections in my country is expected to exceed 3 billion
- Infineon Technologies SECORA™ Pay Bio Enhances Convenience and Trust in Contactless Biometric Payments
- 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 application of several common contact parts in high-voltage connectors of new energy vehicles
- Wiring harness durability test and contact voltage drop test method
- From probes to power supplies, Tektronix is leading the way in comprehensive innovation in power electronics testing
- From probes to power supplies, Tektronix is leading the way in comprehensive innovation in power electronics testing
- Sn-doped CuO nanostructure-based ethanol gas sensor for real-time drunk driving detection in vehicles
- Design considerations for automotive battery wiring harness
- Do you know all the various motors commonly used in automotive electronics?
- What are the functions of the Internet of Vehicles? What are the uses and benefits of the Internet of Vehicles?
- Power Inverter - A critical safety system for electric vehicles
- Analysis of the information security mechanism of AUTOSAR, the automotive embedded software framework
- What knowledge do you need to do LED lighting?
- Various types of timers and clocks for MSP430
- How to use high-speed ADC and DAC with FPGA.pdf
- Lisp Badge (uList Badge)
- UART1 idle interrupt exception occurs when STM32F407VE replaces STM32F429VI
- C++ inheritance important understanding
- [SC8905 EVM Evaluation] + Use of the setting tool SC9805tool
- [IDE] Does IAR have a function module similar to Keil's RTE?
- FPGA Learning Experience
- The best NUCLEO-G474RE has arrived