Oritseweyinmi Henry Ajagbawa utilized causal inference to help examine the interaction between changes in marketing content and Amazon customer behavior.Read More
“Alexa, how do you know everything?”
How Amazon intern Michael Saxon uses his experience with automatic speech recognition models to help Alexa answer complex queries.Read More
Using synthesized speech to train speech recognizers
Data augmentation makes examples more realistic, while continual-learning techniques prevent “catastrophic forgetting”.Read More
Using warped language models to correct speech recognition errors
Model using ASR hypotheses as extra inputs reduces word error rate of human transcriptions by almost 11%.Read More
Spring 2021 Amazon Research Awards recipients announced
The 26 awardees represent 25 universities in 11 countries. Recipients have access to more than 250 Amazon public datasets, and can utilize AWS AI/ML services and tools.Read More
How to make on-device speech recognition practical
Branching encoder networks make operation more efficient, while “neural diffing” reduces bandwidth requirements for model updates.Read More
The science behind Amazon Prime
Amazon’s scientists have developed a variety of scientific models to help customers get the most out of their membership.Read More
BMW Quantum Computing Challenge seeks new solutions to automotive hurdles
Challenge is open to researchers in industry and academia around the globe; the deadline for submissions is Sept. 24, 2021.Read More
Improved Halo Body technology allows customers to take scans in tighter spaces
Scientists updated the system to accurately measure body fat percentage and create personalized 3D models even if there’s not enough room to take a full-body photo.Read More
Alexa & Friends features Yang Liu, principal applied scientist, Alexa AI
Liu discusses her work in speech recognition and understanding, prosody modeling, summarization, and natural language processing.Read More