At smaller vocabulary sizes, tokenizers trained on unannotated data work best.Read More
Body modeling scientist Javier Romero speaks to the value of scientific publishing
Romero is helping lead Amazon’s work in body modeling, and publishing about it, too.Read More
Five Alexa Prize finalists announced
Advances by student teams drive major improvements in users’ experiences with socialbots.Read More
Firecracker: AWS’s open source, minimalist approach to serverless computing
Watch the recording of Marc Brooker’s presentation on Firecracker, an open source virtualization platform.Read More
Making AI a planetary-scale system
Watch the ICLR 2020 keynote presentation by Michael I. Jordan, Amazon scholar and UC Berkeley professor.Read More
Speech synthesizer learns expressive style from one-second voice sample
Users find speech with transferred expression 9% more natural than standard synthesized speech.Read More
Learning graph neural networks with Deep Graph Library
Watch a video tutorial presented by AWS deep learning scientists and engineers at The Web Conference 2020.Read More
Alexa & Friends features Manoj Sindhwani, Alexa Speech vice president
Watch the recording of Manoj Sindhwani’s live interview with Alexa evangelist Jeff Blankenburg.Read More
Amazon scientists author popular deep-learning book
Dive into Deep Learning combines detailed instruction and math with hands-on examples and code.Read More
How Alexa knows when you’re talking to her
Leveraging semantic content improves performance of acoustic-only model for detecting device-directed speech.Read More