WLUG meeting (virtual)

Hi everyone Thanks to Aarons tireless efforts, we can have our WLUG meeting despite COVID-19, though in virtual form via Youtube and Google Hangouts (see links below). As a refresher for the topic: The voice interface represents another big shift in user interfaces, and could be as big a shift as the shift from switches to terminals, the switch from terminals to windowed GUIs, or the switch from full computers to small touchscreen devices. Unfortunately, right now most of these devices are little more than a telephone for talking to a server in the cloud. That is a big problem for privacy, and presents the user with a false choice between access and privacy. Today's computers are capable of handling a verbal interface without requiring a cloud service to handle all of your requests. Aaron Chantrill is one of the developers on the Naomi Project, a free and open source voice assistant (https://projectnaomi.com). It is a plugin based system based on Jasper (http://jasperproject.github.io/), and depending on how the user chooses to configure it, can run totally offline. In this presentation, Aaron would like to introduce people to the Naomi Project, talk about the benefits of a verbal interface, talk about the current architectures of virtual assistants, and ways in which that architecture can be altered to provide better privacy, and also do a comparison of offline speech to text and text to speech solutions, including Pocketsphinx, Mozilla Deepspeech, Kaldi, and Julius. Finally, He will invite people to participate in building and improving Naomi. There is a lot to do and much of it is both engaging and cutting-edge. Aaron recorded a video of his presentation that you can watch here before the virtual meeting: https://youtu.be/8383A_t7iKQ The slides are available as well: https://github.com/aaronchantrill/NaomiPresentation/raw/master/Presentation.... The Google Hangouts link for the Question & Answer session: https://hangouts.google.com/hangouts/_/calendar/ZHJhc2t5QGdtYWlsLmNvbQ.3j6lk... Meetup link: https://www.meetup.com/WaikatoLinuxUsersGroup/events/269578787/ Cheers, Peter -- Peter Reutemann Dept. of Computer Science University of Waikato, NZ +64 (7) 858-5174 http://www.cms.waikato.ac.nz/~fracpete/ http://www.data-mining.co.nz/

On 3/22/20 8:28 PM, Peter Reutemann wrote:
Hi everyone
... Meetup link: https://www.meetup.com/WaikatoLinuxUsersGroup/events/269578787/
Cheers, Peter
Thanks to everyone who tuned in tonight and spent a couple of your last hours of freedom with me. I enjoyed speaking with you all. It was a very interesting conversation and generated some ideas for me, so I hope it was stimulating for you also. Thank you, Aaron

Thanks to everyone who tuned in tonight and spent a couple of your last hours of freedom with me. I enjoyed speaking with you all. It was a very interesting conversation and generated some ideas for me, so I hope it was stimulating for you also.
Likewise. I really enjoyed the discussion about voice assistants. I'm definitely planning on setting up a Naomi system at some stage on a RPi. Do you have any recommendations for a microphone? Cheers, Peter -- Peter Reutemann Dept. of Computer Science University of Waikato, NZ +64 (7) 858-5174 http://www.cms.waikato.ac.nz/~fracpete/ http://www.data-mining.co.nz/

On 3/23/20 9:42 PM, Peter Reutemann wrote:
Likewise. I really enjoyed the discussion about voice assistants. I'm definitely planning on setting up a Naomi system at some stage on a RPi.
Do you have any recommendations for a microphone?
Cheers, Peter
I've had good luck with a cheap ($50 US) USB no-brand conference phone: https://www.amazon.com/gp/product/B078RJK4FW (currently out of stock) I've also had good luck with this USB sound card (2 for $7.95 US): https://www.amazon.com/gp/product/B01KMVSIDM (also out of stock, you supply your own 3.5mm jack microphone and speaker, or use headphones) Finally, I recently purchased a Google AIY Voice Kit ($14.75 US): https://www.amazon.com/gp/product/B075SFLWKX (there is also a Raspberry Pi Zero version now that would not be powerful enough to run Naomi) The USB conference phone and USB card seem to do some echo filtering on device, to reduce the sound picked up by the microphone when Naomi is speaking, while the Google AIY kit does not but is cuter and has a nice green LED light on top. I wrote a plugin for that device to make the LED intensity correspond to volume level in your house, kind of like the volume display on the command line. The Google kit has become my favorite incarnation of Naomi. Most of Naomi development has occurred on the Raspberry Pi 3B, but I am currently running the 4 GiB 4B and quite interested to see what it is capable of as far as deepspeech and kaldi. Sorry most of those are out of stock, but Amazon will provide links to similar devices you might be able to use. Thanks, Aaron
participants (2)
-
Aaron
-
Peter Reutemann