A very nice read is here…..
3. Voice will enter the mainstream of man-machine interaction.
OK, if there is one killer consumer app in 2017, it has to be pervasive use of voice interfaces to applications and devices. Amazon Echo and Google Home broke new ground last year by providing extensible platforms, not just a device that translates voice to search commands. Now, there are already thousands of “skills” these gadgets can learn which will continually expand the devices’ utility in everyday life, from managing grocery lists to playing games to keep us entertained. I believe this is just the beginning and that such devices and software will rapidly augment, but not replace, the touchscreen and keyboard to find information, conduct simple tasks and control customizable appliances.
There are other aspects of this article that are worth reading, but I put this snip here. How does this relate to QUIK is what people always ask?
ALways -on is what QUIK has wanted for years, to push the duty cycle of the CPUs into the yellow or red zone. The listening sensors will become sensors that are always on- listening for the wake up word, while there will be competition we can see as we move forward how this must have feature is implemented across the devices.
Snips from the Eos S3 page
http://www.quicklogic.com/assets/Uploads/EOS-S3-Sensor-Processing-SoC-Platform-Presentation.pdf
n As low as 443μW for always-on voice recognition (voices present 30% of the time). Including a low power
mic, system power as low as 276μA at the battery (assuming 85% efficient regulators and 3.7V battery)
n I2S Interface or PDM interface support
n PDM to PCM decoder for hardware-based, ultra-low power conversion n Sensory Low Power Sound Detector for voice recognition applications
n Speaker-independent fixed trigger “OK Google”
n Speaker-dependent fixed trigger with enrollment
n User defined trigger “Open Sesame!” User defined passphrase “What is my step count?” n Phrase-spotted commands “What is my step count?”
n No slow, cloud processing required; most features run ‘deeply embedded’
n I2S Interface or PDM interface support
n PDM to PCM decoder for hardware-based, ultra-low power conversion n Sensory Low Power Sound Detector for voice recognition applications
n Speaker-independent fixed trigger “OK Google”
n Speaker-dependent fixed trigger with enrollment
n User defined trigger “Open Sesame!” User defined passphrase “What is my step count?” n Phrase-spotted commands “What is my step count?”
n No slow, cloud processing required; most features run ‘deeply embedded’
No comments:
Post a Comment