Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Multimedia Language Technologies Group

We research and develop measurement and evaluation methods to advance and promote the use of technologies that provide more effective access to multimedia and multi-lingual information.

The Multimedia Language Technologies Group (MLTG), established in the 1980s as the Speech Group, has a long history of conducting extensive benchmark testing in human language technology. Our current name reflects the significant growth and complexity of our evaluation portfolio over the decades. MLTG focuses on developing measurement and evaluation methods that facilitate easier access to multilingual and multimedia information while improving human-computer interaction.

Our expertise includes recognizing and transforming information across various modalities—such as speech, text, images, and video—and the fusion of heterogeneous media content. Key focus areas include:

  • Speech & Language: Speech, speaker, and language recognition, machine translation, and information retrieval.
  • Visuals & Video: Image and video processing, visual recognition, and 2D/3D shape analysis.
  • Systems & Quality: Image quality assessment and interoperable digital media access.

Projects and Programs

Guardians of Forensic Evidence

Ongoing
The program addresses critical challenges including a gap between high research accuracy and a lack of ease-of-use in real-world applications, as well as the need for improved generalization capability and robustness against post-processing and anti-forensics filters. The specific image deepfake...

Speaker and Language Recognition

Ongoing
Current Speaker and Language Recognition Activities: Speaker Recognition Evaluation series: (1996-) A biennial NIST evaluation of fully automated text-independent speaker recognition technology. Human Assisted Speaker Recognition Evaluation series: (2010- ) A biennial NIST evaluation of approaches...

Text REtrieval Conference (TREC)

Ongoing
Its purpose was to support research within the information retrieval community by providing the infrastructure necessary for large-scale evaluation of text retrieval methodologies. In particular, the TREC workshop series has the following goals: to encourage research in information retrieval based...

Publications

2025 NIST GenAI Text Challenge Evaluation Plan

Author(s)
Seungmin Seo, Hariharan Iyer, Yooyoung Lee
The NIST Generative AI (GenAI) Text Challenge is an evaluation program designed to probe the capabilities and limitations of generative AI models from three...

2025 NIST GenAI (Pilot): Code Challenge Evaluation Plan

Author(s)
Peter Fontana, Yooyoung Lee, Hariharan Iyer, Sonika Sharma
We are launching a pilot for measuring and evaluating unit tests generated by Artificial Intelligence (AI) for testing elementary python code. This pilot will...

Awards

Ellen Voorhees receives Gerald Salton Award

Congratulations to Ellen Voorhees on receiving the Gerard Salton Award at the ACM Conference on Research and Development in Information Retrieval (SIGIR). The Gerard Salton Award is presented every three years to an individual who has made “...

Ellen Voorhees Wins Ron Brown Excellence in Innovation Award

Dr. Ellen M. Voorhees was announced as the recipient of the Ron Brown Excellence Award in Innovation as part of the 73rd Annual Department of Commerce award winners. The Secretary of Commerce noted that "former Secretary of Commerce Ron Brown saw...

Contacts

Was this page helpful?