METHOD AND APPARATUS FOR DETECTING SPOOFING CONDITIONS

Patent №

US 10,692,502

Granted

2020-06-23

Filed 2018

Owner

PINDROP SECURITY, INC.

Lab

AI components

5

ml · nlp · vision · speech · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15910387

An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.

Machine learningNatural languageVisionSpeechAI hardwareG10L 17/02G10L 17/00G10L 17/04G10L 17/06G10L 17/18G10L 19/02G10L 25/24G10L 25/30+1 more

AI classification

Speech1.00
Machine learning1.00
Vision0.99
Natural language0.96
AI hardware0.68
Knowledge representation0.01
Evolutionary computation0.00
Planning0.00

Ownership

PINDROP SECURITY, INC.

assignment · 451150885

Assignors

KHOURY, ELIE, NAGARSHETH, PARAV, PATIL, KAILASH, GARLAND, MATTHEW

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC