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.
Speaker Recognition Subcommittee
The Speaker Recognition Subcommittee focuses on standards and guidelines related to the practice of speaker recognition, voice data collection, measurement, transmission, and retrieval.
Officers | Members | Standards | Other Work Products
Officers
Larry Kincaid, Subcommittee Chair, Sandia National Laboratories
John Hansen, Subcommittee Co-Vice Chair, University of Texas at Dallas
Jennifer Stathakis, Subcommittee Executive Secretary, National Institute of Standards and Technology (NIST)
Members
Dana M. Delger, Self Employed (Legal Task Group representative)
Sandra Disner, University of Southern California
Stephanie Domitrovich, Administrative Office of Pennsylvania Courts (Legal Task Group representative)
Ewald Enzinger, Eduworks Corporation
Stephen Gibbs, U.S. Federal Government
Erica Gold, California State University San Marcos
Zayan Haq, Department of Homeland Security
David Marks, Federal Bureau of Investigation
Jack Prothero, National Institute of Standards and Technology (NIST) (Statistics Task Group representative)
Emily Whitmarsh, Defense Forensics and Biometrics Agency
Jennifer Williams, University of Southampton
Cindy (Ya Yang) Xiong, University of Massachusetts (Human Factors Task Group representative)
Speaker Recognition Affiliate List
Standards
On the OSAC Registry
- AES 76-2022 AES Standards for Audio Forensics - Speech Collection Guidelines for Speaker Recognition: Interviewing at a Temporary Location (added May 2, 2023)
- OSAC 2023-N-0023 Standard Guide to the Forensic Speaker Recognition Landscape (added December 3, 2024)
At an SDO for Further Development & Publication
- OSAC 2023-N-0023 Standard Guide to the Forensic Speaker Recognition Landscape (OSAC Proposed Standard on the Registry)
Under Development
- OSAC 2025-S-1002-ND Dataset Collection For Forensic Speaker Recognition
Other Work Products
Process Maps
Reference Documents
- Is this a Deepfake? This is an introductory guide to synthetic, repurposed, and deepfake digital media (images, audio, video, etc.).
- Desktop Version, April 22, 2025.
- Trifold Version, April 22, 2025.
Research & Development Needs
- See the research and development needs identified by the Speaker Recognition Subcommittee.
Webinars, Presentations & Training Videos
- Speaker Recognition Webinar, "Various Evaluation Metrics Used in Speaker Recognition," May 7, 2025.
Technical Guidance Documents
- Issues in Data Processing and Relevant Population Selection, November 2022.
Discipline-Specific Bibliographies and Bibliographic References
These documents may contain information to help forensic scientists, judges, lawyers, researchers, and other readers better understand the nature, scope, and foundations of the individual disciplines as currently practiced. The identification of these documents does not represent an endorsement by OSAC or NIST. Only standards that are posted on the OSAC Registry and Technical Guidance documents, are endorsed by OSAC. The referenced documents may be subject to copyright. Note: Subcommittee position statements or responses to data collections by the subcommittee do not necessarily represent the position of OSAC or NIST.