daisy stanton (@daisystanton) 's Twitter Profile
daisy stanton

@daisystanton

Deep learning speech research @GoogleAI. Let's build The Young Lady's Illustrated Primer! Spare time: classical music, science journal clubs, MTB, dance.

ID: 7339982

linkhttps://ai.google/research/people/DaisyStanton calendar_today09-07-2007 04:40:10

125 Tweet

663 Followers

467 Following

daisy stanton (@daisystanton) 's Twitter Profile Photo

TL;DR we use math to make synthetic speech do moar funny/expressive things. Listen to e.g. "That's right! shouted the Queen"; we're trying to get "Baseline" to sound more like "Reference": google.github.io/tacotron/publi…

Sundar Pichai (@sundarpichai) 's Twitter Profile Photo

Detecting deepfakes is one of the most important challenges ahead of us. Following our release of a synthetic audio dataset in Jan, we're releasing a large dataset of visual deepfakes to support researchers working on synthetic video detection #GoogleAI ai.googleblog.com/2019/09/contri…

daisy stanton (@daisystanton) 's Twitter Profile Photo

If you train an end-to-end text-to-speech model whose attention fails to align, you can get hilarious descents into speech madness like this: google.github.io/tacotron/publi…. Sadly, Eric Battenberg has reduced the frequency that we'll get to cry with laughter in our office over these...

daisy stanton (@daisystanton) 's Twitter Profile Photo

New research from my brilliant colleagues! At long last, direct-to-waveform Tacotron -- using multi-scale normalizing flows (read RJ Skerry-Ryan's thread if you have FOMO and want to learn what those words mean). Everyone's still smiling and kicking ass through pajamafromhome. 🚀

New research from my brilliant colleagues! At long last, direct-to-waveform Tacotron -- using multi-scale normalizing flows (read <a href="/rustyryan/">RJ Skerry-Ryan</a>'s thread if you have FOMO and want to learn what those words mean). Everyone's still smiling and kicking ass through pajamafromhome. 🚀
daisy stanton (@daisystanton) 's Twitter Profile Photo

Google Research is excited to announce ... TACOSPAWN! It's a TTS model that can speak in human voices that don't exist: google.github.io/tacotron/publi… We learn a prior over the speaker embedding space of a many-speaker Tacotron: arxiv.org/abs/2111.05095

daisy stanton (@daisystanton) 's Twitter Profile Photo

Yes, my team is actually actually hiring! If you love getting into the weeds of generative modeling (RS) or build machine learning models like a ninja (SWE), reach out! 🌠

daisy stanton (@daisystanton) 's Twitter Profile Photo

If you haven't listened to Lex's June 30 interview with George Hotz (and especially if you think you hate Hotz), do. It was very good and very entertaining. I recommend audio over video: lexfridman.com/george-hotz-3-…

Climate Change AI (@climatechangeai) 's Twitter Profile Photo

We're excited to announce the Climate Change AI Summer School 2024!☀️ Are you an #AI expert who wants to tackle #ClimateChange? Are you a #climate expert trying to use #ML in your work? Are you curious about the topic? Apply & register now! Learn more👉climatechange.ai/events/summer_…

We're excited to announce the <a href="/ClimateChangeAI/">Climate Change AI</a> Summer School 2024!☀️

Are you an #AI expert who wants to tackle #ClimateChange? Are you a #climate expert trying to use #ML in your work? Are you curious about the topic?

Apply &amp; register now! Learn more👉climatechange.ai/events/summer_…
OpenBallot (@openballotapp) 's Twitter Profile Photo

We're thrilled to open sign-ups for OpenBallot in time for the November San Francisco election! See 40+ voter guides in one place, and use our tool to fill out your ballot. You can keep it private or share with friends: openballot.app/guides

OpenBallot (@openballotapp) 's Twitter Profile Photo

Want a more bike-friendly SF? 🚲 Check out SF Bicycle Coalition's voter guide on OpenBallot along with 40+ others to help shape the city's future! 🗳️🌉 openballot.app/guides/9cba2a3…

daisy stanton (@daisystanton) 's Twitter Profile Photo

Eric is the powerhouse that got RNN-based TTS models to generalize to utterance lengths not seen in training via Dynamic Convolution Attention (DCA). Now he's at it again with Transformer-based models, using interpolated relative position biases in a novel alignment mechanism 💪