Research

  • Research Areas
  • Impact Areas

Algorithms & Theory

Foundational work that includes complexity, parallel computing and game theory

AI & Machine Learning

Spanning natural language processing, deep-learning, computer vision and more

Computational Biology

Understanding disease via epigenomics, gene regulation and bioinformatics

Computer Architecture

How CPUs, memory and other systems are designed and organized

Graphics & Vision

Teaching computers to interpret, create and animate visual data

Human-Computer Interaction

Software and hardware that let us naturally interact with technology

Programming Languages & Software Engineering

From compilers and verification to software design and engineering

Robotics

Vision, actuation, sensing and manipulation of machines

Security & Cryptography

Developing technologies to prevent and recover from cyber-attacks

Systems & Networking

From distributed systems and databases to wireless

Filter options
Filter options

Filter options Close

Role

Media

Opportunities Available

Research Areas

Impact Areas

Reset Filters

1 Group Results matching all criteria

2 Project Results matching all criteria

1 People Results matching all criteria

3 Group Results

11 Project Results

Project

Automatic Speech Recognition

Spoken Language Systems Group
Automatic speech recognition (ASR) has been a grand challenge machine learning problem for decades. Our ongoing research in this area examines the use of deep learning models for distant and noisy recording conditions, multilingual, and low-resource scenarios.

Leads

Hao Tang

Hao Tang

weining_hsu

Wei-Ning Hsu

Harwath-headshot

David Harwath

MIT CSAIL Spoken Language Systems PhD student

Sameer Khurana

Di-Chia Chueh Profile Image

Di-Chia Chueh

Jim Glass

Jim Glass

Research Areas

AI & Machine Learning
Human-Computer Interaction

Impact Areas

Big Data
Education
Entertainment
Health Care
Internet of Things

Project

Computational Knitting: Patterning and Shaping for Everyone

Computational Fabrication Group
Knitting is the new 3d printing. It has become popular again with the widespread availability of patterns and templates, together with the maker movements. Lower-cost industrial knitting machines are starting to emerge, but we are still missing the corresponding design tools. Our goal is to fill this gap.

Alexandre Kaspar

Leads

Alexandre Kaspar

Research Areas

Graphics & Vision
Human-Computer Interaction

Impact Areas

Entertainment
Manufacturing
 

Alexandre Kaspar

Project

Efficient Communication for Human-Machine Teams

Interactive Robotics Group
Our goal is to develop collaborative agents (software or robots) that can efficiently communicate with their human teammates. Key threads involve designing algorithms for inferring human behavior and for decision-making under uncertainty.

X. Jessie Yang

Vaibhav V. Unhelkar

JShah-headshot

Julie Shah

Leads

Vaibhav V. Unhelkar

JShah-headshot

Julie Shah

Research Areas

Human-Computer Interaction
Robotics

Impact Areas

Manufacturing

X. Jessie Yang

 

Vaibhav V. Unhelkar

JShah-headshot

Julie Shah

Project

Unsupervised Speech Processing

Spoken Language Systems Group
All humans process vast quantities of unannotated speech and manage to learn phonetic inventories, word boundaries, etc., and can use these abilities to acquire new word. Why can't ASR technology have similar capabilities? Our goal in this research project is to build speech technology using unannotated speech corpora.
Jim Glass

Leads

image

Jennifer Drexler

Yu-An Chung (Andy)

Yu-An Chung

MIT CSAIL Spoken Language Systems PhD student

Sameer Khurana

Harwath-headshot

David Harwath

Research Areas

AI & Machine Learning
Human-Computer Interaction

Impact Areas

Big Data
Education
Health Care
Jim Glass

12 People Results

Jim Glass

PI
Core/Dual

Jim Glass

Senior Research Scientist
speech and language processing
Jim Glass
T 253-1640
RM 32-G444

Lead

Spoken Language Systems Group
Designing Information-Rich Embedding Spaces
Unsupervised Learning of Interpretable Representations from Sequential Data
Fact-Checking and Reasoning
Speaker Verification and Diarization
Automatic Speech Recognition
Language and Dialect Identification

Member

Wait-learning: Intelligent Systems for Making Productive Use of Wait Time
Using Computers to Eat Healthier
Low-Power Speech Processing Circuits
Crossing the Vision-Language Boundary
Unsupervised Speech Processing
Arabic Language Processing
Health-related Biomarkers from Speech
Community Question Answering
Understanding Language Representations in Deep Learning Models
speech and language processing

Henry Lieberman

Research Scientist
Henry Lieberman is a Research Scientist at MIT CSAIL, in AI and HCI.
Henry Lieberman is a Research Scientist at MIT CSAIL, in AI and HCI.

7 News Results

Researchers at MIT’s Microsystems Technology Laboratories have built a low-power chip specialized for automatic speech recognition. With power savings of 90 to 99 percent, it could make voice control practical for relatively simple electronic devices.
AI & Machine Learning Human-Computer Interaction Energy Internet of Things Manufacturing

Voice control everywhere

The butt of jokes as little as 10 years ago, automatic speech recognition is now on the verge of becoming people’s chief means of interacting with their principal computing devices. In anticipation of the age of voice-controlled electronics, MIT researchers have built a low-power chip specialized for automatic speech recognition. Whereas a cellphone running speech-recognition software might require about 1 watt of power, the new chip requires between 0.2 and 10 milliwatts, depending on the number of words it has to recognize.

Voice control everywhere

A prototype of a new speech-controlled nutrition-logging system allows users to verbally describe the contents of a meal. The system then parses the description and automatically retrieves the pertinent nutritional data.
AI & Machine Learning Human-Computer Interaction Health Care

Voice-controlled calorie counter

For people struggling with obesity, logging calorie counts and other nutritional information at every meal is a proven way to lose weight. The technique does require consistency and accuracy, however, and when it fails, it’s usually because people don't have the time to find and record all the information they need.A few years ago, a team of nutritionists from Tufts University who had been experimenting with mobile-phone apps for recording caloric intake approached members of the Spoken Language Systems Group at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), with the idea of a spoken-language application that would make meal logging even easier.

Voice-controlled calorie counter