US-12626708-B1 - Hybrid spectro-morse acoustic authentication system and method

US12626708B1US 12626708 B1US12626708 B1US 12626708B1US-12626708-B1

Abstract

An audio authentication and identity verification system and method that encodes dynamic cryptographic information across the audible and inaudible spectrum (0 Hz→30 kHz, scalable to 124 kHz). A rolling acoustic signature simultaneously embeds identity, time, date, and GPS location using a hybrid of frequency shift keying (FSK), phase shift keying (PSK), Morse style pulse duration modulation, and time domain multiplexing. To guarantee post-event privacy and integrity, the system further incorporates a dual custody audio architecture in which every authenticated recording is split into complementary bit interleaved segments stored separately, and the decryption key is fragmented via Shamir 3-of-5 secret sharing—preventing unilateral access or tampering. The system establishes a tamper proof, real time, and offline capable authentication layer that functions in air, through conventional microphones, and via dedicated emitter hardware.

Inventors

Mulakkal Thomas George
Bosky Cherin Varghese
Senthil Kumar Muthian

Assignees

both Inc.

Dates

Publication Date: 20260512
Application Date: 20250829

Claims (15)

1 . A method for audio authentication and identity verification, comprising: emitting an inaudible audio signature, wherein the inaudible audio signature includes a unique identifier, a time, a date, and a set of location coordinates; modulating the inaudible audio signature using one or more modulation schemes selected from amplitude modulation, frequency modulation, phase modulation, pulse-duration modulation, frequency-shift keying (FSK), phase-shift keying (PSK), or any combination thereof; encoding the inaudible audio signature within an audio content by overlaying the inaudible audio signature as at least one carrier at a lane-center frequency or as a set of carriers within a designated band of the audio content, wherein a payload encodes at least one of the unique identifier, the time, the date, or the set of location coordinates as a direct alphanumeric symbol mapped to at least one tone and/or at least one pulse duration; splitting the encoded audio content into at least two complementary bit segments, storing one of the at least two complementary bit segments on a device, and storing one of the at least two complementary bit segments in a cloud database; decrypting, via a decryption key, the at least two complementary bit segments; and recording a decryption event on an immutable ledger.
2 . The method of claim 1 , further comprising shifting the inaudible audio signature across multiple sub-bands within the full 0 Hz-124 kHz spectrum.
3 . The method of claim 1 , wherein the inaudible audio signature further includes a date-of-birth.
4 . The method of claim 1 , further comprising storing the inaudible audio signature as uncompressed audio as a high-resolution WAV file at 48 kHz or higher.
5 . The method of claim 1 , further comprising concealing the inaudible audio signature by applying acoustic dithering, noise shaping, and randomized scheduling to the inaudible audio signature.
6 . The method of claim 1 , further comprising mapping the unique identifier directly to acoustic symbols, including, to the at least one tone and/or the at least one pulse duration without hashing.
7 . A system for audio authentication and identity verification, comprising: a near-field communication (NFC)-enabled piezoelectric emitter device operable to playback or emit an inaudible audio signature, wherein the inaudible audio signature includes a unique identifier, a time, a date, and a set of location coordinates; and a dual custody and shared key privacy architecture; wherein the system is operable to modulate the inaudible audio signature using one or more modulation schemes selected from amplitude modulation, frequency modulation, phase modulation, pulse-duration modulation, frequency-shift keying (FSK), phase-shift keying (PSK), or any combination thereof, wherein an audio content is encoded with the inaudible audio signature by overlaying the inaudible audio signature as at least one carrier at a lane-center frequency or a set of carriers within a designated band of the audio content; wherein the dual custody and shared key privacy architecture is operable to split the encoded audio content into at least two complementary bit segments, wherein one of the at least two complementary bit segments is stored on a device, and wherein one of the at least two complementary bit segments is stored in a cloud database; and wherein the audio content is operable to be verified by verifying the identity, the time, the date, and the set of location coordinates of the encoded inaudible audio signature.
8 . The system of claim 7 , wherein the inaudible audio signature is stored as uncompressed audio including as a high-resolution WAV file at 48 kHz or higher.
9 . The system of claim 7 , further comprising an anti-jamming module operable to shift the inaudible audio signature across multiple sub-bands within the full 0 Hz-124 kHz spectrum.
10 . The system of claim 7 , wherein the inaudible audio signature further includes a date-of-birth.
11 . The system of claim 7 , wherein parity blocks and watermark fragments are embedded into the inaudible audio signature.
12 . A method for audio authentication and identity verification, comprising: emitting an inaudible audio signature, wherein the inaudible audio signature includes a unique identifier, a time, a date, and a set of location coordinates; modulating the inaudible audio signature using one or more modulation schemes selected from amplitude modulation, frequency modulation, phase modulation, pulse-duration modulation, frequency-shift keying (FSK), phase-shift keying (PSK), or any combination thereof, encoding the inaudible audio signature within an audio content by overlaying the inaudible audio signature as a single-line carrier at lane-center frequency onto frequency carriers of the audio content into the ultrasonic band; splitting the encoded audio content into at least two complementary bit segments, storing one of the at least two complementary bit segments on a device, and storing one of the at least two complementary bit segments in a cloud database; decrypting, via a decryption key, the at least two complementary bit segments, wherein the decryption key is partitioned into five shards using a 3-of-5 Shamir secret sharing scheme; recording a decryption event on an immutable ledger; decoding the inaudible audio signature via at least one of band-pass filtering, time-frequency analysis including fast Fourier transform analysis, short-time Fourier transform analysis, or Goertzel analysis, envelope or correlation detection, phase retrieval, checksum validation, and/or error-detecting validation; and verifying the audio content by verifying the identity, time, date, and location data of the encoded inaudible audio signature.
13 . The method of claim 12 , wherein the time-frequency analysis further comprises a Goertzel filter bank tuned to expected carriers.
14 . The method of claim 12 , wherein the inaudible audio signature further includes a date-of-birth.
15 . The method of claim 12 , further comprising storing the inaudible audio signature as uncompressed audio at a high-resolution WAV file at 48 kHz or higher.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to audio authentication and identity verification, and more specifically to a lightweight, scalable method of encoding a legible digital identity within high frequency audio content. 2. Description of the Prior Art It is generally known in the prior art to provide audio-based authentication or watermarking. Prior art patent documents include the following: US Patent Publication No. 2024/0362738 for System for mitigating the problem of deepfake media content using watermarking by inventors Alattar, et al., filed Mar. 4, 2024, and published Oct. 31, 2024, is directed to watermarking media content, in combination with blockchain and distributed storage networks, which prevents the proliferation of Deepfake content. Digital watermarks are embedded in the audio and video tracks of video clips of trusted content producers at the time the videos are captured or before they are distributed. The watermarks are detected at the social media network's portals, nodes, and back ends. The embedded watermark imparts a unique identifier to the video, that links it to a blockchain. The watermarks also allow video source tracking, integrity verification, and alteration localization. The watermark detectors can be standalone software applications, or they can be integrated with other applications. They are used to perform three main tasks: (1) they alert the Internet user when he watches an inauthentic news video, so that he may discard it, (2) they prevent a Deepfake content from propagating through the network (3) they perform forensic analysis to help track and remove Deepfake content postings. US Patent Publication No. 2024/0127833 for System and methods thereof for audio authentication by inventors Goshen, et al., filed Dec. 26, 2023, and published Apr. 18, 2024, is directed to a system and method for authenticating audio. A method includes sampling audio captured by an array of microphones based on sound produced by audio sources; generating an audio channel per audio source for the audio captured by the array of microphones, wherein each audio channel is a portion of the sampled audio produced by a respective audio source; generating a unique acoustic signature (UAS) for the audio sources by processing portions of the sampled audio of each audio source in order to create processed audio, wherein the UAS is a set of acoustical parameters representing acoustical properties of each audio source; generating a hashing value based on the UAS and the audio channel per audio source; and encoding the processed audio using the hashing value in order to generate encoded audio, wherein the encoded audio is authenticated using the hashing value and the UAS. U.S. Pat. No. 11,477,156 for Watermarking and signal recognition for managing and sharing captured content, metadata discovery and related arrangements by inventor Lord, filed Aug. 31, 2020, and issued Oct. 18, 2022, is directed to content being identified using watermarking and/or other content recognition combined with contextual metadata, which facilitates identification and correlation with other content and metadata when it is posted to a network. U.S. Pat. No. 10,964,332 for Audio communication method and apparatus for watermarking an audio signal with spatial information by inventor Gautama, filed Sep. 20, 2017, and issued Mar. 30, 2021, is directed to an apparatus and method for speech communication. An audio transmit processor captures at least two audio signals from an audio source, and processes the at least two audio signals to provide a mono audio signal and a non-audio signal comprising spatial information representative of the direction of the audio source. The audio transmit processor combines the non-audio signal with the mono audio signal by watermarking; and transmits the watermarked audio signal. An audio receive processor receives a watermarked audio signal and extracts a mono audio signal and a non-audio signal comprising spatial information from the watermarked audio signal. The audio receive processor processes the mono audio signal and spatial information to generate at least two output audio signals. U.S. Pat. No. 10,777,210 for Key phrase detection with audio watermarking by inventor Garcia, filed Mar. 19, 2019, and issued Sep. 15, 2020, is directed to methods, systems, and apparatus, including computer programs encoded on computer storage media, for using audio watermarks with key phrases. One of the methods includes receiving, by a playback device, an audio data stream; determining, before the audio data stream is output by the playback device, whether a portion of the audio data stream encodes a particular key phrase by analyzing the portion using an automated speech recognizer; in response to determining that the portion of the audio data stream encodes the particular key phrase, modifying the audio data stream to include an audio watermark; and providing the modifie