Customer-obsessed science


-
May 17, 2022Papers focus on speech conversion and data augmentation — and sometimes both at once.
-
May 12, 2022Multimodal training, signal-to-interpretation, and BERT rescoring are just a few topics covered by Amazon’s 21 speech-related papers.
-
May 10, 2022Topics range from the predictable, such as speech recognition and signal processing, to time series forecasting and personalization.
-
-
May 22 - 27, 2022
-
May 22 - 27, 2022
-
-
May 16, 2022Matt Taddy, vice president of Amazon’s Private Brands business, is the coauthor of Modern Business Analytics: Practical Data Science for Decision Making, a primer for those who want to gain the skills to use data science to help make decisions in business and beyond.
-
May 12, 2022NAIAC will advise the president on a range of issues related to artificial intelligence.
-
April 27, 2022Event’s speaker roster expands for keynotes, innovation spotlights, and leadership sessions.
-
April 25, 2022Advanced machine learning systems help autonomous vehicles react to unexpected changes.
-
2022We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module. RAC consists of a standard base image encoder fused with a parallel retrieval branch that queries a non-parametric external memory of pre-encoded images and associated text snippets. We apply RAC to the problem of long-tail classification and
-
2022Conditional neural text generation models generate high-quality outputs, but often concentrate around a mode when what we really want is a diverse set of options. We present a search algorithm to construct lattices encoding a massive number of generation options. First, we restructure decoding as a best-first search, which explores the space differently than beam search and improves efficiency by avoiding
-
IWSLT 20222022This paper describes Amazon Alexa AI’s implementation for the IWSLT 2022 shared task on formality control. We focus on the unconstrained and supervised task for en→hi (Hindi) and en→ja (Japanese) pairs where very limited formality annotated data is available. We propose three simple yet effective post editing strategies namely, T-V conversion, utilizing a verb conjugator and seq2seq models in order to rewrite
-
2022Estimating a semantically segmented bird’s-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation. However, they show an increase in localization error with distance from the camera. While such an increase in error is entirely expected – localization is harder at distance – much of the drop in performance can be attributed to the cues used by current
-
2022Speech Emotion Recognition (SER) has several use cases for Digital Entertainment Content (DEC) in Over-the-top (OTT) services, emotive Text-to-Speech (TTS) engines and voice assistants. In this work, we present a Multi-Lingual (MLi) and Multi-Task Learning (MTL) audio only SER system based on the multi-lingual pre-trained wav2vec 2.0 model. The model is fine-tuned on 25 open source datasets in 13 locales
-
May 05, 2022The UCLA Science Hub seeks to address challenges to humanity through research using artificial intelligence, bringing together academic and industry scientists.
-
February 15, 2022University teams will compete to develop a bot that best responds to customer commands in a virtual world.
-
April 07, 2022The JHU + Amazon Initiative for Interactive AI (AI2AI) will be housed in the Whiting School of Engineering.
Working at Amazon
View allMeet the people driving the innovation essential to being the world’s most customer-centric company.
View all
-
May 09, 2022"I hope we have accelerated HIV vaccine development by providing findings that we and others can build on."
-
May 03, 2022How a math-loving student travelled 7,000 miles to pursue a passion and wound up becoming an applied scientist.
-
May 02, 2022Former Amazon intern George Boateng is using machine learning and mobile tech to bridge Africa’s digital divide.