MATCH (Multimodal AcousTic Characterization of Hoax calls) a System for Hoax Maritime Distress Call Detection
Award last edited on: 7/16/2022

Sponsored Program
Awarding Agency
Total Award Amount
Award Phase
Solicitation Topic Code
Principal Investigator
Doug Cairns

Company Information

Vadum Inc

601 Hutton Street Suite 109
Raleigh, NC 27606
   (919) 341-8241
Location: Single
Congr. District: 04
County: Wake

Phase I

Contract Number: 70RSAT22C00000043
Start Date: 5/5/2022    Completed: 10/4/2022
Phase I year
Phase I Amount
Vadum will develop MATCH (Multimodal AcousTic Characterization of Hoax calls) a novel machine learning (ML) system to automatically and accurately detect deception in maritime Search and Rescue (SAR) audio distress calls and aid Coast Guard watchstanders in disambiguating hoaxes from legitimate calls. MATCH will substantially alleviate the burden on Coast Guard watchstanders by continuously monitoring the VHF distress channel for traffic, analyzing detected distress calls, and issuing warnings and alerts when hoax calls are present.MATCH will incorporate expert-identified and learned features that profile the acoustic signature of the caller, lexical traits, and characteristics of the acoustic scene (background environment) to confirm or invalidate the authenticity of the distress call.Legitimate distress calls typically happen in a specific acoustic scene.MATCH will utilize a novel classifier to recognize and validate legitimate acoustic scenes. The multi-mode multi-feature nature of the MATCH architecture will accommodate variances in regional dialects and accents and be expandable to include additional features representative of intoxicated mariners. The MATCH solution is adaptable to other domains such as 911 call centers, law enforcement agencies and commercial voice phishing attack mitigation.

Phase II

Contract Number: 70RSAT23C00000027
Start Date: 4/14/2023    Completed: 4/13/2025
Phase II year
Phase II Amount
Vadum will continue improving MATCH (Multimodal AcousTic Characterization of Hoax calls), an innovative machine learning system that automatically monitors maritime Search and Rescue (SAR) VHF channel(s).Vadum showed feasibility for the system and developed key components in a six-month Phase I effort.In Phase II, Vadum will further develop and refine MATCH into a real-time prototype that continuously monitors the VHF distress channel and provides automated call triage to separate out distress traffic and detect hoax calls.MATCH utilizes acoustic, lexical, and contextual features to analyze a call for signs of a hoax.The information is presented to the watchstander in an interpretable manner, pointing them to the specific aspects of a call that could indicate a hoax.In Phase II, Vadum will continue to improve MATCH and bring it closer to maturity, while working with the Coast Guard to ensure that the system integrates into end-user environments.MATCH can be extended to a variety of DHS, DoT, DHHS, DoD, and commercial use cases, such as at first responder communications centers, to provide a level of confidence in the veracity of 9-1-1 calls, 9-8-8 calls, or to detect swatting calls. The technology could also be used by automated border control agents at airports, by DoD Programs of Record, and by the Intelligence Community in support of intel collection.