Is this your business? Claim it to manage your IP and profile
Belonging to the AONSens™ Neural Network series, the AON1020 is crafted for both voice and audio recognition alongside other sensor applications. Recognized for its hectic performance in minimal power environments, AON1020's AI processing engine is available in Verilog RTL, making it accessible for use in ASIC and FPGA technologies. Engineered for scenarios like human activity detection through sensor applications, this IP provides always-on multi-wake-word detection and on-device voice command recognition. Its features ensure adaptability even in environments characterized by noise, offering stable performance irrespective of user or environmental changes. The AON1020's robust architecture accommodates sensor fusion applications, enhancing its capability in multi-sensor environments where it can decipher activities like running or walking. This offers developers potent solutions in expanding markets such as smart home automation and industrial IoT applications.
The AON1000 represents the pinnacle of edge hardware and software AI solutions. It is designed to deliver top-notch efficiency and accuracy in voice and sound recognition, rendering it perfect for the Internet of Things (IoT), wearables, and smart home applications. It stands out for its low power consumption while maintaining impressive performance even in noisy environments, thanks to proprietary neural network architecture. AON1000 supports always-on applications with capabilities like multi-wake-word detection and on-device voice command recognition. Its adaptive voice activity detection and context awareness make it highly versatile, enabling robust voice controls for consumers. Having high accuracy in challenging auditory conditions ensures it remains a dependable choice for developers. Designed as part of the AONVoice™ processor family, the AON1000 excels in processing wake word detection, voice commands, acoustic event detection, and speaker identification. Its ability to offer top-tier accuracy per microwatt makes it a leader in its field, adaptable for integration in both standalone chips and sensors. Additionally, this IP includes a customized data augmentation tool for training, making it highly sought after for super-low-power applications.
AON1010 is designed as a highly optimized neural network core specifically for voice and audio recognition. It processes microphone data efficiently, suitable for applications ranging from voice recognition to sound recognition. Delivered in Verilog RTL, the AON1010 is suitable for incorporation into ASIC and FPGA designs, making it adaptable to varied technologies. This IP supports always-on environments with features like multi-wake-word detection and adaptive voice activity detection, which are key for continuous listening applications. Additionally, it provides high accuracy even in noisy environments, and is speaker-independent, meaning it can adapt to user and environmental variabilities without loss of performance. This adaptability allows it to handle multiple commands simultaneously and with precision. With notable capabilities in speaker identification and context awareness, the AON1010 is optimized for integration into high-precision voice control systems. Its proprietary processing engine ensures substantial power savings, critical for battery-operated devices and systems requiring persistent voice interaction functionality.
AONDenoise offers groundbreaking single-microphone AI-driven denoising technology that brings clarity to audio experiences. Through the use of advanced AI algorithms, this solution is tailored to significantly minimize background noise with minimal latency, under 1 ms. Utilizing around 50K parameters, this edge AI technology is compact yet powerful, providing noise reduction presets for various environments such as babble, wind, and keyboard uses. The denoiser can isolate desired audio input in diverse settings, vastly enhancing auditory clarity for users in even the most challenging environments like concerts or city streets. AONDenoise's software suite allows for extensive user customization, permitting specific adjustments while ensuring audio quality is preserved. Its ability to discern distinct noises accurately demonstrates its capability for applications demanding precise noise management.
Join the world's most advanced semiconductor IP marketplace!
It's free, and you'll get all the tools you need to discover IP, meet vendors and manage your IP workflow!
No credit card or payment details required.
Join the world's most advanced AI-powered semiconductor IP marketplace!
It's free, and you'll get all the tools you need to advertise and discover semiconductor IP, keep up-to-date with the latest semiconductor news and more!
Plus we'll send you our free weekly report on the semiconductor industry and the latest IP launches!
To evaluate IP you need to be logged into a buyer profile. Select a profile below, or create a new buyer profile for your company.
