NSA Georgia Opens New Audio-Forensics Lab
Open PDFDocument date: 2007-02-22
Type: SIDtoday
Pages: 2
Genre: newsletter
Banner: DYNAMIC PAGE -- HIGHEST POSSIBLE CLASSIFICATION IS TOP SECRET // SI / TK // REL TO USA AUS CAN GBR NZL
Classification: TOP SECRET SI TK
Dissemination: REL TO USA AUS CAN GBR NZL
The document discusses the launch of a new audio-forensics lab at NSAG (National Security Agency Georgia) designed to enhance the processing and analysis of intercepted voice communications. The lab, funded through the Senior Language Technology Authority (SLTA), will focus on resolving language processing challenges for language analysts by improving the intelligibility and quality of foreign-language voice intercepts.
BABBLEQUEST, HLT
People mentioned:
Mercer, Marti Hix
Countries:
-
Tags:
audio forensics, NSAG, voice communications, SLTA, language analysis, language analysts, voice intercept, audio intercept, speech processing, speaker identification, age, gender
Identifier:
2007-02-22-NSA-Georgia-Opens-New-Audio-Forensics
PDF SHA-256:
9a3e03173cddf4e2509925da32e45ca922b58ffaf3330865a9173b463a724021
My notes
DYNAMIC PAGE -- HIGHEST POSSIBLE CLASSIFICATION IS
TOP SECRET // SI / TK // REL TO USA AUS CAN GBR NZL
SIDtoday
(U//FOUO) NSA Georgia Opens New Audio-Forensics Lab
FROM: Marti Hix Mercer
Chief, Corporate Communications, NSAG
Run Date: 02/22/2007
(S//SI//REL) New lab aims to help analysts fully capitalize on intercepted voice communications from our targets.
(S//SI//REL) The start of the new year also saw the start of a powerful new capability at NSAG - a new audio-forensics lab funded through the Senior Language Technology Authority (SLTA). The lab -- the first of its kind anywhere within the Extended Cryptologic Enterprise -- initially will serve NSAG, with a vision toward expanding to accomodate external requests. It aims to help solve critical language processing problems confronting Language Analysts. As envisioned, the lab will provide dedicated, on-site, state-of-the-art solutions to address the problems that impair the processing of critical foreign language voice intercept.
(S//SI//REL) The intent is to provide a capability to language analysts as quickly as possible and support them in the evaluation of that capability. According to [REDACTED] the lab's audio engineer, the lab is in the "early walking" phase of a crawl-walk-run approach. As the audio forensics lab at NSAG succeeds, the SLTA hopes to build similar labs at the other major regional cryptologic centers.
(S//SI//REL) [REDACTED] in the audio-forensics lab
(TS//SI//REL) [REDACTED] directly supports NSAG language analysts by enhancing hearability and intelligibility of audio intercepts. He does this by performing audio restoration or audio forensic analysis to help language analysts determine the content and context of high-priority GWOT*-related audio intercepts. [REDACTED] Iso works on fundamental problems associated with speech, speaker identification, age and gender determination, psychological stress in voice, speech intelligibility/comprehension, speech signal enhancement, and masking the effects of noise on speech. Specific goals of the lab are to:
- Filter and enhance unintelligible/poor-quality voice intercept;
- Assist NSAG language analysts or tactical forces with voice/speaker identification to aid in recognition of high value individuals or detainees;
- Identify, isolate, and extract background speakers and audio sounds;
- Develop signal databases containing speaker, context, background, and other information with the ability to index, sort, and retrieve in real time;
- Collaborate in the analysis and processing of complex voice intercept.
(S//SI//REL) The audio lab provides an unparalleled opportunity to support prototype testing and spiral development. In addition, the lab acts as a test-bed for language processing capabilities developed elsewhere. The lab will partner with the SLTA, the Research Directorate, the Human Language Technology Program Management Office, and Speech Services -- the providers of operational speech technologies ( BABBLEQUEST ) to customers across the Enterprise -- to test capabilities developed from these organizations before placing them in an operational environment.
(U//FOUO) The audio lab has an open architecture so that it can readily accept new capabilities, tools, and technologies as they are developed. In addition, the lab will be net-centric so that language analysts will be able to collaborate with the lab virtually. Further, if and when similar audio labs are set up elsewhere throughout the SIGINT Enterprise, they can be networked together to leverage and utilize existing capabilities.
(U//FOUO) Finally, in addition to being a fully functioning audio forensics lab, the room itself is designed to be a showcase for NSAG. Consequently, it reflects an impressive, high-tech, visually appealing environment that is pleasant to work in. [REDACTED] is very much looking forward to working with language experts throughout the Enterprise in order to increase the lab's capacity to improve the Agency's capabilities. As a plaque in the lab states, "Supporting the mission never sounded so good."
(S//SI//REL) At work in the lab
(U) Notes:
* (U) GWOT = Global War on Terrorism
"(U//FOUO) SIDtoday articles may not be republished or reposted outside NSANet
without the consent of S0121 (DL sid comms)."
DYNAMIC PAGE -- HIGHEST POSSIBLE CLASSIFICATION IS
TOP SECRET // SI / TK // REL TO USA AUS CAN GBR NZL
DERIVED FROM: NSA/CSSM 1-52, DATED 08 JAN 2007 DECLASSIFY ON: 20320108
Published in the Same Report
(10 of 21 documents)
-
RT10 Initiative Overview [pdf]
Overview document for RT10, "Real-time, distributed architecture for mobile (tactical) and fixed (national) operational environments"
Programs: RT10 · COBRA FOCUS · GREENDRAGON · GOLDMINER · JUGGERNAUT · MATTERHORN · OBELISK · SORTINGHAT · INFOVIS · SHARPFOCUS2 · TOGA · SORTINGLEAD · GLOBALREACH · VOICERT · QUADRASPECTRE · RENOIR · ANALYSTSNOTEBOOK · OCTAVE · HLT · DRT · GEOT · InnoVisions -
Alert: Voice Masking Is Discovered in SIGINT SIDtoday [pdf]
This March 2007 post from the internal NSA newsletter SIDToday draws attention to voice-masking technology used by subjects of surveillance to frustrate the agency’s voice-recognition efforts.
-
Tips for a Successful Quick Reaction Capability SIDtoday [pdf]
In response to Iranian President Ahmadinejad’s 2007 visit to New York, the NSA’s Iran Government and Leadership branches launched a Quick Reaction Capability (QRC) to gather time-sensitive intelligence. The QRC focused on enhanced collection techniques, collaboration across departments, and efficient data management to analyze the extensive communications traffic during the event, resulting in valuable leads on Iranian leadership activities and diplomatic plans.
People: Ahmadinejad, Mahmoud -
New RT-RG Overview Video Available on NSANet SIDtoday [pdf]
The NSA's Meade Operations Center released a 10-minute video overview of the Real-Time Regional Gateway (RT-RG), a tool suite designed for forward-deployed analysts. The suite enables faster access to real-time metadata and reporting, improving tactical support for military operations, with new functionalities being developed for use in Afghanistan and beyond.
-
Voice Biometrics Capability Proven During Recent Technology Demonstration SIDtoday [pdf]
The Coordinate Operational Resources for Voice Exploitation Technology (CORVET) project, managed by the Expeditionary SIGINT Services Office (ESSO), demonstrated a promising capability for voice biometrics that could be used in security operations to identify individuals based on voice characteristics. Similar to the long-established method of fingerprinting, CORVET aims to create a database of voice models that could be used for identification in various contexts, such as detention and force-protection scenarios.
-
Alvin, Simon, and... Al Qaeda? Finding Modified Voice in SIGINT Traffic SIDtoday [pdf]
This SIDtoday article discusses the use of voice modification technology by Al-Qaeda and other extremist groups to evade identification in SIGINT traffic. It highlights the development of the HLT Lite software by R64, which can automatically detect modified voices in intercepted communications, enabling the identification of targets even when traditional voice recognition fails.
-
Come to SID's Identity Intelligence (I2) Day Conference and See Your Target in a Whole New Light! SIDtoday [pdf]
This SIDtoday article promotes NSA's Identity Intelligence (I2) Day Conference, highlighting the importance of using SIGINT tools and techniques to track individuals across time and space. It emphasizes the growing role of biometrics, biographic data, and digital footprints in identifying and targeting foreign persons of interest, with insights from key speakers and case studies.
-
SIGINTers Use Human Language Technology to Great Advantage, Isolate Conversation about Threat to US Official SIDtoday [pdf]
In 2010, the Special Collection Service in Mexico City began using Human Language Technology (HLT) to streamline voice collection and analysis, significantly improving efficiency. By rapidly filtering through large volumes of audio data, HLT helped isolate critical intelligence, such as identifying a conversation related to a bomb threat targeting a U.S. Embassy official, all within minutes instead of hours.
Programs: HLT -
Innov8 Voice Analytics Experiment Profile [pdf]
This document outlines Phase 1 of a Voice Analytics experiment conducted by GCHQ in partnership with the NSA, testing the ingestion and processing of voice data through the DISTILLERY platform on GHOSTMACHINE hardware. The experiments evaluate independent, parallel, and linked analytics (SAD, GID, LID), as well as dynamic resource management, to ensure accurate, scalable, and compliant voice processing in a Joint Collaboration Environment.
Marking: TOP SECRET -
Voice Fax User Group Minutes December 2010 [pdf]
This GCHQ document is a NSA/GCHQ meeting record from December 2010 detailing the deployment of voice analytics, including speech activity detection, speaker identification, and language identification, integrated with tools like Google Earth to map locations of target communications. It outlines ongoing and planned speaker ID operations against specific targets, including militant leaders and foreign officials, demonstrating the operational use of voice recognition for intelligence collection and geolocation.
Related Documents
-
Tips for a Successful Quick Reaction Capability SIDtoday [pdf]
In response to Iranian President Ahmadinejad’s 2007 visit to New York, the NSA’s Iran Government and Leadership branches launched a Quick Reaction Capability (QRC) to gather time-sensitive intelligence. The QRC focused on enhanced collection techniques, collaboration across departments, and efficient data management to analyze the extensive communications traffic during the event, resulting in valuable leads on Iranian leadership activities and diplomatic plans.
People: Ahmadinejad, Mahmoud -
GCHQ Visit to NSA on Voice Analytics Systems [pdf]
This document is a GCHQ report detailing a late-November (2007?) visit to NSA’s R64 division focused on collaboration in language identification (LID) and speaker identification (SID) systems, including sharing models and research insights. It also describes NSA tools like Hotzone and Voice RT for real-time voice analysis, and mentions an upcoming visit from the CLEAR consortium to address challenges in speech intelligibility and audio recovery for intercepted communications.
-
Human-Language Technology -- Everywhere SIDtoday [pdf]
The best Human Language Technology (HLT) functions "behind the desktop" making sure the analyst receives relevant, filtered information. In the near future, analysts will have more and better HLT at their disposal.
People: Kulman, AnitaThe Intercept ↗ (2019-05-29) -
Classification Guide for Human Language Technology (HLT) Models (May 18, 2011) [pdf]
This document is an NSA administrative policy document that establishes the rules for what information regarding speech analytics remains public versus what must be kept secret. It explicitly confirms that the NSA possesses automated tools for gender, language, dialect, and speaker recognition, as well as speech-to-text and phonetic tokenization. While the existence of these capabilities is unclassified, the specific data used to "train" the models and the actual identity of targeted speakers are protected at the SECRET level.
Programs: HLT -
Click ... Click ... Click ... What's the Number? SIDtoday [pdf]
NSA staff working on the BABBLEQUEST project can listen on phone lines and, by analyzing acoustic signals, determine what numbers a given telephone is dialing, whether from a digital or old-fashioned rotary phone.
People: Cusmariu, AdolfThe Intercept ↗ (2019-05-29)