Speaker and Language Recognition Projects

The Multimodal Information Group's speaker and language recognition program includes several activities contributing to speaker and language recognition technology and metrology advancements, primarily through systematic and targeted evaluations.

Since 1996, the Multimodal Information Group has coordinated evaluations of speaker and language recognition technology through our Speaker Recognition Evaluation (SRE) and Language Recognition Evaluation (LRE) series. NIST-led open evaluations such as SRE and LRE have provided successful test beds for research, development and evaluation of speaker and language recognition technologies.  The evaluation series have remained agile, adapting to changes in technology capabilities and research direction.   Participation in these NIST evaluation activities is open to all researchers that find the tasks of interest and are able to abide by the particular evaluation's task protocols and rules.

NIST also organizes and implements evaluations for sponsored programs that focus on specific aspects of speaker recognition, such as the IARPA BEST program, and is working toward developing data collection, storage and interoperability standards for voice in conjunction with the FBI.

Current Speaker and Language Recognition technology evaluation activities:

• Speaker Recognition Evaluation: A biennial NIST evaluation of text-independent speaker recognition technology. More information on our current/recent activities can be found here.
  
• Human Assisted Speaker Recognition:In 2010 NIST held a pilot evaluation of approaches combining human expertise with automatic speaker recognition technology.More information on our current/recent activities can be found here.
• Language Recognition Evaluation: A biennial NIST evaluation of language recognition technology.
• BEST of BEST: In 2011 NIST will be running an evaluation of speaker recognition technology in support of the IARPA BEST program.
• Investigatory Voice Biometrics: In 2009 NIST began a joint effort with the FBI to conduct research supporting the creation of voice biometric standards for the U.S. Government.