Human language technologies
Researching software and systems that bridge the linguistic divide between people and machines to make communicating with computers as natural as speaking with family and friends.
Microsoft Research Blog
Research Focus: Week of February 19, 2024
In this issue: CaaSPER: vertical autoscaling algorithm dynamically maintains optimal CPU utilization; Improved scene landmark detection for camera localization runs faster, uses less storage; ESUS simplifies usability questionnaires for technical products and services.
Publication
Generative Representational Instruction Tuning
Project
ELaTE
Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like ELaTE is a zero-shot text-to-speech (TTS) system that can generate natural laughing speech from any speaker based on a speaker prompt to mimic the voice characteristic, a…
Publication
An Interactive Agent Foundation Model
Tool
Orca-2-13B
Orca 2 is a finetuned version of LLAMA-2. It is built for research purposes only and provides a single turn response in tasks such as reasoning over user given data, reading comprehension, math problem solving…
Tool
Orca-2-7B
Orca 2 is a finetuned version of LLAMA-2. It is built for research purposes only and provides a single turn response in tasks such as reasoning over user given data, reading comprehension, math problem solving…
Microsoft Research Blog
Research Focus: Week of January 22, 2024
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Join Microsoft Research Forum (opens in new tab)…
Video
Deep Learning Acoustic Model in Microsoft Cortana Voice Assistant
Deep Learning Acoustic Modeling has been widely deployed to real-world speech recognition products and services that benefit millions of users. In this talk, I will first briefly describe selected developments and investigations at Microsoft to…