No one has ever
collected large datasets of people whose speech is hard
for others to understand. They’re not
used in training the speech recognition model. I mean, the game is
to record things and then have it recognize
things that you say that aren’t in the training set. Dimitri recorded 15,000 phrases. It wasn’t obvious that
this was going to work. He just sat there and
he kept recording. [Dimitri speaking] You can see that
it’s possible to make a speech recognizer
work for Dimitri. It should be possible
to make it work for many people. Even people who can’t speak because they’ve lost
the ability to speak. The work that Shanqing
has done on, you know, voice utterances. [hum] From sounds alone
you can communicate. But there might be other
ways of communicating. Most people with
ALS end up using an on-screen keyboard
and having to type each individual letter
with their eyes. For me, communicating
is sloooooooow. Steve might crack a joke and it’s related to
something that happened, you know,
a few minutes ago. The idea is to
create a tool so that Steve can train machine
learning models himself to understand his
facial expressions. [basketball crowd cheering] [air horn sounds] Michael: [laughs] it works! to be able to laugh to be able
to cheer to be to boo, things that
seem maybe superfluous, but actually are so
core to being human. I still think this is only
the tip of the iceberg. We’re not even scratching the
surface yet of what is possible. If we can get
speech recognizers to work with small numbers of people, we’ll learn lessons which we can then combine to build something that really works for everyone. ♪♪

Project Euphonia: Helping everyone be better understood
Tagged on:                 

46 thoughts on “Project Euphonia: Helping everyone be better understood

  • May 7, 2019 at 5:53 pm
    Permalink

    Nice

    Reply
  • May 7, 2019 at 5:56 pm
    Permalink

    just kill those who aren't perfect

    Reply
  • May 7, 2019 at 5:57 pm
    Permalink

    Nice

    Reply
  • May 7, 2019 at 6:00 pm
    Permalink

    Really good idea!👍👏

    Reply
  • May 7, 2019 at 6:00 pm
    Permalink

    Awesome <3 Thanks Google!!! Go #Vegan for compassion !!! Watch What The Health on netflix! Namaste !

    Reply
  • May 7, 2019 at 6:10 pm
    Permalink

    This is so amazing good job Google 🙏

    Reply
  • May 7, 2019 at 6:17 pm
    Permalink

    Amazing! truly a noble work

    Reply
  • May 7, 2019 at 6:33 pm
    Permalink

    Wooohooo nice and brave devs, good work

    Reply
  • May 7, 2019 at 6:41 pm
    Permalink

    Steaw Hawking 2

    Reply
  • May 7, 2019 at 6:43 pm
    Permalink

    OMG, Google you are a good company. This is so nice to help people with problems and don't go for the money. Thank you

    Reply
  • May 7, 2019 at 6:56 pm
    Permalink

    Helo

    Reply
  • May 7, 2019 at 6:57 pm
    Permalink

    Amazing. You got all my support

    Reply
  • May 7, 2019 at 7:02 pm
    Permalink

    Another reason to love Google

    Reply
  • May 7, 2019 at 7:55 pm
    Permalink

    makes sense

    Reply
  • May 7, 2019 at 8:17 pm
    Permalink

    Make this blue if you love Google ❤️
    👇🏻(I'm gifting 1000 subscribers!)

    Reply
  • May 7, 2019 at 8:31 pm
    Permalink

    Seeing how anti free speech google is they're probably going to ban you if you try to say naughty words for "muh hate speech"

    Reply
  • May 7, 2019 at 8:38 pm
    Permalink

    Is amazing! I like you, Google!!

    Reply
  • May 7, 2019 at 10:45 pm
    Permalink

    There is actually already a large database of audio recordings of people who stutter. Here's the link. Please like this so that hopefully google can see it.
    https://fluency.talkbank.org/

    Reply
  • May 8, 2019 at 1:09 am
    Permalink

    Amazing!!

    Reply
  • May 8, 2019 at 2:05 am
    Permalink

    Awesome job that's my comment

    Reply
  • May 8, 2019 at 5:22 am
    Permalink

    So needed! We need more more more of these types of things.

    Reply
  • May 8, 2019 at 7:30 am
    Permalink

    My grandfather's speech in his last days due to stroke really got a lot worse…we rarely understood what he wanted to say
    Since then I had imagined of such a technology but in India you've no opportunity to make dreams a reality

    Thanks to Google for giving future stroke patients and their families a ray of hope

    Reply
  • May 8, 2019 at 7:55 am
    Permalink

    google Thanks from all people of pakistan ….hope you bring all your products outside usa and india someday

    Reply
  • May 8, 2019 at 10:00 am
    Permalink

    👏🏼❤️

    Reply
  • May 8, 2019 at 1:14 pm
    Permalink

    AOUDOBILLAHIMINAACHCHAITANIERRAJIMIBISMIALLAHIARRAHMANIARRAHIMIWALAHAWLAWALAKOWWATAILLABILLAHIALALIYALADIMI.

    Reply
  • May 9, 2019 at 3:54 am
    Permalink

    god bless google

    Reply
  • May 9, 2019 at 4:04 am
    Permalink

    This is great. I think there’s a welcome space for people with Down Syndrome. Their speech sounds and grammatical patterns are predictable as a population category and typically very consistent as individuals. I assume that’s helpful in training speech output devices. Having speech output increases a person’s independence for socializing, work, taking transportation, as well as safety in the community. I hope you’d consider working with this group.

    Reply
  • May 9, 2019 at 4:20 am
    Permalink

    You know what’s fun? Robbing and beating rich google employees on cannery row when they show up with their half million dollar sports cars. So much fun!

    Reply
  • May 9, 2019 at 6:52 am
    Permalink

    I watched this during the keynote and I teared up. I hope this project helps a lot more people. I am so supportive of this. Thanks Google. 🙂

    Reply
  • May 10, 2019 at 11:47 am
    Permalink

    L
    Yes

    Reply
  • May 10, 2019 at 10:44 pm
    Permalink

    Excellent

    Reply
  • May 11, 2019 at 10:41 am
    Permalink

    Amazing work! Speech recognition should absolutely be made to work for people with any kind of speech impediment from multiple sclerosis to being scottish.

    Reply
  • May 11, 2019 at 11:37 am
    Permalink

    start by recognizing women high pitch voices.

    Reply
  • May 11, 2019 at 6:21 pm
    Permalink

    Why are there dislikes on this video? I don't understand.

    Reply
  • May 12, 2019 at 1:06 pm
    Permalink

    This was the stand out feature of I/O for me, giving people back their voice who have had it taken from them.

    If anyone you know has problems with their speech please go to g.co/euphonia

    Reply
  • May 12, 2019 at 11:03 pm
    Permalink

    Google is the best freaking company in the world.

    Reply
  • May 13, 2019 at 2:03 am
    Permalink

    Good job Google, thanks for this project. I hope it will be success.

    Reply
  • May 14, 2019 at 10:40 am
    Permalink

    Respected sir I have a fresh content of the PC and mobile games, +919426175921.

    Reply
  • May 16, 2019 at 10:21 am
    Permalink

    any published papers?

    Reply
  • May 20, 2019 at 3:45 pm
    Permalink

    The future is bright

    Reply
  • June 2, 2019 at 9:02 am
    Permalink

    Thank You for doing this Google! This is absolutely awesome!!!
    If you need more test subjects (users) during development phase, please let me know. I'm nonverbal and I would be a great candidate for this!
    When you are ready for Alpha or Beta testing, I know a large group of special needs friends at our local university would gladly help out during the QA phase.

    Reply
  • July 7, 2019 at 4:29 pm
    Permalink

    Good job, I thought Dimitry was speaking Russian.

    Reply
  • July 24, 2019 at 11:41 pm
    Permalink

    Cover the captions and watch this video. I dare you. Thanks Google.

    Reply
  • August 13, 2019 at 11:27 pm
    Permalink

    The simpler issue is the John Oliver joke about voice recognition systems force you to have a American accent

    Reply
  • September 5, 2019 at 1:01 am
    Permalink

    I cried

    Reply

Leave a Reply

Your email address will not be published. Required fields are marked *