All items tagged with on-device (22)

On-Device Intelligence: Apple Makes AI Make Sense

June 13, 2024 by Joao Martins

On-Device Intelligence: Apple Makes AI Make Sense

Apple's Worldwide Developers Conference (WWDC) 2024 keynote unveiled Apple Intelligence and was another historic moment for the Cupertino company. Apple Intelligence will be implemented in this year's and future devices, and will arrive with iOS 18, iPadOS 18, macOS Sequoia, and watchOS 11 updates. Everywhere in the demonstrations of the new features, we could see clear signs of artificial intelligence doing its thing in the background. A true milestone in the history of computing and consumer technology - when AI started to make sense.

Gaudio Lab Launches "Just Voice Recorder" AI-Powered Recording App

May 24, 2024 by Joao Martins

Gaudio Lab Launches "Just Voice Recorder" AI-Powered Recording App

Gaudio Lab continues to expand its AI audio technology efforts in multiple fronts with very interesting results. The latest AI audio separation technology developments from the company have now been condensed in the form of a new app called "Just Voice Recorder." This is a cutting-edge mobile recording application powered by AI noise cancellation technology that is extremely useful to record interviews, dictation and recording on the field. It simply makes voice recordings clean and clear using voice separation and enhancement.

SoundHound On-Chip Voice AI Enabled by NVIDIA DRIVE

March 19, 2024 by Joao Martins

SoundHound On-Chip Voice AI Enabled by NVIDIA DRIVE

SoundHound AI is evolving its approach with voice artificial intelligence (Voice AI) and announced a completely new implementation of an in-vehicle voice assistant that uses a large language model (LLM) completely on the edge, running on the NVIDIA DRIVE platform. The solution combines SoundHound Chat AI running completely on-device and delivers Generative AI with no connectivity required for speech-to-meaning voice interactions.

Sensory Unveils Automotive AI Platform at CES 2024

January 9, 2024 by Joao Martins

Sensory Unveils Automotive AI Platform at CES 2024

Sensory, the Californian company at the forefront of voice recognition is now set to capture the automotive industry's attention with the introduction of its state-of-the-art AI automotive platform. For CES 2024, Sensory is promoting a new embedded AI solution, combining advanced voice and vision technologies, that the company promises will not only redefine driving safety but will also revolutionize user-vehicle interaction and set a new standard in automotive technology.

Qualcomm Unveils S7 Pro Snapdragon Sound Platform With Micro-Power Wi-Fi and 24-bit/192kHz Lossless Streaming

October 24, 2023 by Joao Martins

Qualcomm Unveils S7 Pro Snapdragon Sound Platform With Micro-Power Wi-Fi and 24-bit/192kHz Lossless Streaming

During its Snapdragon Summit event Qualcomm unveiled the latest S7 and S7 Pro Gen1 Sound platforms, which will soon power a new generation of advanced audio products. The new platforms offer five times the compute power, three times the DSP processing power, and almost 100 times on-device AI processing power compared to the previous generation. A real differentiator is the use of micro-power Wi-Fi to extend wireless audio range and support for up to 192kHz lossless music quality in the S7 Pro.

AONDevices Introduces Super Low-Power, Low-Latency, Customizable Edge AI Speech Enhancement

October 16, 2023 by Joao Martins

AONDevices Introduces Super Low-Power, Low-Latency, Customizable Edge AI Speech Enhancement

AONDevices, the AI processing company from Irvine, California, announced AONDenoise, a compact, efficient edge AI denoising solution that enable customizable noise cancellation running in real-time, completely on-device. Designed for applications that require minimal power and latency, AONDenoise is one of the smallest denoising algorithms available, making it an ideal AI speech enhancement for use in hearing aids, wireless earbuds, and wearables.

NXP's VIT Speech to Intent Engine with Natural Language Understanding Enables Voice Interactions On-Device

October 3, 2023 by Joao Martins

NXP's VIT Speech to Intent Engine with Natural Language Understanding Enables Voice Interactions On-Device

NXP Semiconductors announced the VIT Speech to Intent engine, a natural language understanding engine that leverages edge computing to enable local voice control. Part of NXP’s Voice Intelligent Technology (VIT) software suite, the VIT Speech to Intent engine rivals cloud-based systems' performance, and does not require a cloud connection, supporting improved user privacy in consumer electronics and automotive applications.

Sensory TrulyHandsfree 7.0 Improves Voice Recognition Accuracy

September 18, 2023 by audioXpress Staff

Sensory TrulyHandsfree 7.0 Improves Voice Recognition Accuracy

Sensory announced the launch of TrulyHandsfree 7.0, the latest iteration of its groundbreaking voice recognition software for low-power wake words and small command sets. As pioneers in wake word and custom voice assistants, now focusing their efforts in embedded voice and biometric AI technology, Sensory's latest version of TrulyHandsfree improves accuracy, size, and power consumption, all key metrics for the advancement of voice recognition applications.

Ambiq Removes Noise in Real-Time with Speech Enhancement AI for Connected Applications

August 29, 2023 by Joao Martins

Ambiq Removes Noise in Real-Time with Speech Enhancement AI for Connected Applications

Ambiq introduced the Neural Network Speech Enhancer (NNSE), the latest addition to its neuralSPOT's Model Zoo - a highly optimized AI model that effectively removes background noise from speech on the device in real-time, allowing clean speech capture in noisy environments. As with all Ambiq Model Zoo components, NNSE includes scripts and tools to help developers add speech de-noising capabilities to their applications.

MediaTek Enhances On-Device Generative AI Processing

August 28, 2023 by Cristina Costa

MediaTek Enhances On-Device Generative AI Processing

MediaTek is already powering more than two billion connected edge devices every year and now the company confirmed that it is working closely with Meta's Llama 2 next-generation open-source Large Language Model (LLM). Combining this recently announced LLM with its latest APUs and NeuroPilot AI Platform, MediaTek aims to build a complete edge computing ecosystem designed to accelerate AI application development on smartphones, consumer connected devices, vehicles, smart home, etc.

«
1
2
3
»