Leveraging semantic content improves performance of acoustic-only model for detecting device-directed speech.Read More
ICASSP: What “signal processing” has come to mean
Alexa scientist Ariya Rastrow on the blurring boundaries between acoustic processing and language understanding.Read More
Computer vision researcher Thomas Brox enjoys university and industry roles
Award-winning scientist joined Amazon team in Tübingen earlier this year.Read More
Forecasting big time series: theory and practice
View recording of tutorial presented at The Web Conference 2020.Read More
“Pseudo-labels”, negative examples help Alexa match skills to customer requests
Letting a machine learning system label its own examples improves performance.Read More
Nine videos about explainable AI in industry
Industry collaborators create nine-part series that provides theoretical underpinnings for explainable AI and industry case studies.Read More
Locating multiple sound sources from raw audio
An end-to-end deep-learning-based solution circumvents the “permutation problem”.Read More
ICLR: The AI conference that helped redefine the field
Amazon’s Stefano Soatto on how learning representations came to dominate machine learning.Read More
Advances in text-to-speech technologies help computers find their voice
Generating natural sounding, human-like speech has been a goal of scientists for decades.Read More
How robots can adapt to new tasks — quickly
New approach to meta-reinforcement learning minimizes the need for costly interactions with the environment.Read More