Research Tools: code, datasets, & models

P family of languages, compilers and runtimes.

This template shows how to incorporate a vega-lite specification as a PowerBI custom visual.

Neural Phrase-based Machine Translation (NPMT) explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a…

Microsoft Hands-Free Sound Machine is a WPF XAML application that works with a number of Tobii eye tracking devices and leverages the audio and MIDI APIs in Windows 10 to play both sampled audio and…

MMdnn is a comprehensive, cross-framework solution to convert, visualize and diagnosis deep neural network models. The “MM” in MMdnn stands for model management and “dnn” is an acronym for deep neural network. Basically, it converts…

Computational photography research explores the power of AI and computer vision, pushing the limits of what is possible by helping people fully and easily utilize technology with innovative photography apps and services.

This dataset provides an unprecedented number of sensor recordings (405 in total), including multiple IMUs and infrared (IR) sensors deployed on 24 individual body segments. Together there are over 3 hours of data (sampled at…

Language modelling is a key component of many NLP systems, but comparing language models (LMs) in a fair way can be difficult.  LM Challenge is a small, cross platform Python library for evaluating and investigating…

The Microsoft Speech Language Translation Corpus release contains conversational, bilingual speech test and tuning data for English, Chinese, and Japanese collected by Microsoft Research. The package includes audio data, transcripts, and translations and allows end-to-end…

This library implements Frodo, a lattice-based key exchange based on the Learning with Errors (LWE) problem. The library uses Frodo’s “recommended parameters”.