WIll take a brief look at it here... QUIK...... . During Q2, we will enhance the voice trigger and voice recognition capabilities of our EOS S3 sensor processing platform with the integration of acoustic echo cancellation technology, which is commonly known as AEC. AEC significantly improves the ability of a smartphone, wearable or IoT device to recognize a voice trigger and the ensuing user commands in noisy environments. This is an enabling technology for always-on voice in a number of common use cases. An example of this would be enabling a smartphone, wearable or an IoT device to recognize a voice trigger at the same time it is being used to play music. With AEC, you could be streaming Pandora from your smartphone and still use your voice to trigger your smartphone to bring up navigation without muting the song or looking away from the road.
Sensory a month ago........ Sensory Boosts Performance of Embedded Wake Word and Speech Recognition by Infusing Smarter AI Santa Clara, Calif., April 27, 2017 – Sensory’s TrulyHandsfree with new shallow learning technique stays small and gets smarter, more accurate, and more robust to noiseSensory, a Silicon Valley-based company focused on improving the user experience and security of consumer electronics through state-of-the-art embedded AI technologies, today announced that it has made significant updates to the embedded AI in itsTrulyHandsfree™ technology to dramatically boost its performance and accuracy, while staying small and low power.A lot of text has been dropped so all can get the mapping with no distraction....Advanced Signal Processing for Voice Barge-In and Far-Field Speech RecognitionTrulyHandsfree 5.0 also features a new voice barge-in feature, enabled with Sensory’s proprietary Acoustic Echo Cancellation (AEC) technology. Users can interrupt devices while playing voice prompts, music or other sounds by saying the trigger phrase to control music playback by voice, or provide any other kind of supported speech commands. This provides a more fluid voice user interface experience. Sensory’s new AEC technology is tuned specifically to maximize speech recognition system accuracy. This not only boosts the performance of the embedded TrulyHandsfree speech recognizer, but also any cloud-based speech recognition system that the speech requests are passed to.dropped text again so most wont miss the key thing...Same Low-Power and Efficient Footprint“The demand for voice user interfaces continues to grow rapidly and TrulyHandsfree 5.0 will allow more manufacturers to incorporate low cost, low power voice user interfaces on device without sacrificing the cloud accuracy,” said Todd Mozer, CEO of Sensory. “TrulyHandsfree 5.0 offers the most advanced and efficient embedded AI technologies we’ve ever created.Additionally, we’ve set the bar higher than ever before for speech recognition accuracy by applying our new proprietary echo cancellation and noise reduction algorithms that we are confident will boost far-field voice performance for IoT devices of all kinds.”TrulyHandsfree is the most widely deployed embedded speech recognition engine in the world, having enabled a hands-free voice user experience on more than 2 billion devices from leading brands worldwide. Additionally, Sensory can deliver voice triggers for all major IoT cloud services, including Amazon AVS, Apple Siri, Google Assistant and Microsoft Cortana, and provide developer support for cloud service interfaces on Linux, Android, iOS and Windows as well as support for dozens of proprietary DSPs, microcontrollers, smart microphones and other low-power embedded devices. ******************************************************************************* set the bar higher than ever before for speech recognition accuracy by applying our new proprietary echo cancellation and noise reduction algorithms that we are confident will boost far-field voice performance for IoT devices of all kinds.”So Note that being on the right side of Moore's law allows us to add great IP..Using Sensory as a mental model....This is it ;-)Up from the archives for the casual reader...QuickLogic and Sensory Partner to Provide Always-Listening, Deeply Embedded Voice Recognition at Ultra-Low PowerSUNNYVALE, CA -- (Marketwired) -- 07/30/15 -- QuickLogic Corporation (NASDAQ: QUIK) Hardened system blocks specifically designed for voice processing applications provide extremely power efficient, always-listening voice capability Less than 350 microAmps always-on voice trigger Supports advanced voice processing, including voice recognition, without cloud connection requirement QuickLogic Corporation (NASDAQ: QUIK), the innovator of ultra-low power programmable sensor processing solutions, today announced that it is partnering with voice and vision technology industry leader Sensory Inc. to deliver TrulyHandsfree™ software the world's most advanced voice recognition solution, deeply embedded in its newEOS™ S3 sensor processing platform. The hardened system blocks included in the EOS sensor processing SoC platform are designed to provide integrated voice trigger and command and control functionality at ultra-low power levels, enabling a vast array of voice-driven applications without the need for a connection to cloud services.And now Sensory has NEW AEC algos in version 5.0. QUIK has expertise now in partitioning.It has the eFPGA block, it has the MCU to run these new deep learning noise algos.... nice.... at a very important TIME, this will help those circuit board trials in China?KEY point.... Sensory stood alone and based its audio on Neural Networks TWENTY yrs ago...This gives them a SMALL footprint, it will be good for the smallest hearable too For long time holders, many that are here....start to realize that what is in the past WAS NOT a waste....we learned how to partition between the FFE, the eFPGA, and the MCU....that skill set is vital for these top tier players. That is a skill that QUIK will be using a LOT going forward. Its a a good thought and better feeling for me that all those things of the past will help insure the FUTURE )) Use the addition of Sensory handsfree 5.0 as a mental model...we can improve and improve and improve from S3 to the 60% added space of the S4.
No comments:
Post a Comment