ANTI-SPOOFING

• US 20150088509A1
• Filed: 09/24/2014
• Published: 03/26/2015
• Est. Priority Date: 09/24/2013
• Status: Active Grant

• Current Assignee: Cirrus Logic Incorporated
• Original Assignee: Agnitio s.l. (Microsoft Corporation)
• Inventors: Rodriguez, Luis Buera, Gimnez, Alfonso Ortega, Avils-Casco, Carlos Vaquero
• Granted Patent: US 9,767,806 B2
• Time in Patent Office: Days
• US Class Current: 704/243
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

System for classifying whether audio data received in a speaker recognition system is genuine or a spoof using a Gaussian classifier and method for classifying whether audio data received in a speaker recognition system is genuine or a spoof using a Gaussian classifier.

Claims

1. System for classifying whether audio data received in a speaker recognition system is genuine or a spoof using a Gaussian classifier.

2. System according to claim 1, wherein one, two, three, four or more Gaussians are used to model the genuine region of audio data parameters and/or wherein one, two, three, four or more Gaussians are used to model the spoof region of audio data parameters

and/or

wherein the system is adapted to be exclusively used to determine if received audio data is genuine or a spoof.

3. System according to claim 1, wherein the considered parameters of the audio data comprise a spectral ratio and/or a feature vector distance and/or a Medium Frequency Relative Energy (MF) and/or Low Frequency Mel Frequency Cepstral Coefficients (LF-MFCC)

and/or

wherein the feature vector distance is calculated with regard to average feature vectors derived from enrollment data used for enrollment of 1, 2, 3, or more speakers into the Speaker Recognition System.

and/or

wherein the feature vector distance is calculated with regard to a constant value provided.

4. System according to claim 3, wherein the feature vector distance is calculated using Mel Frequency Cepstrum Coefficients.

5. System according to claim 3, wherein a Cauer approximation is used when extracting LF-MFCC and/or wherein a Cauer approximation is used when extracting MF

and/or

wherein Hamming windowing is used when extracting LF-MFCC and/or wherein Hamming windowing is used when extracting MF

and/or

wherein 1, 2, 3 or more or all LF-MFCC comprised in the parameters describing the audio data are selected, e.g. with develop data from known loudspeakers which may be used in replay attacks and/or with a priori knowledge

and/or

wherein when calculating 1, 2, 3 or more or all LF-MFCC comprised in the parameters describing the audio data, for the estimation of the spectrum autoregressive modelling and/or linear prediction analysis are used

and/or

wherein the filter for calculating MF is built to maintain certain relevant frequency components of the signal, which are optionally selected according to the spoof data which should be detected, e.g. according to the frequency characteristics of loudspeakers which are typically used for spoof in replay or other attacks.

6. System according to claim 1, wherein initial parameters for the Gaussian classifier are derived from training audio data using an Expectation Maximization algorithm, wherein the training data is chosen depending on the information that the Gaussian classifier should model

and/or

wherein initial parameters for the Gaussian classifier are provided.

7. System according to claim 1, wherein new parameters for the Gaussian classifier are found by adaptation of previous parameters of the Gaussian classifier using adaptation audio data.

8. System according to claim 1, wherein the number of available samples of adaptation audio data is considered in the adaptation process.

9. System according to claim 1, wherein at least one of

the mean vector(s) and/or the covariance matrices and/or the a priori probability of one, two, three, four or more Gaussians representing the genuine region of audio data parameters are adapted, or

the mean vector(s) and/or the covariance matrices and/or the a priori probability of one, two, three, four or more Gaussians representing the spoof region of audio data parameters are adapted.

10. System according to claim 1, wherein the enrollment audio data comprises the adaptation audio data.

11. System according to claim 1, wherein the adaptation audio data comprises at least one of genuine audio data or spoof audio data.

12. System according to claim 1, wherein the adaptation audio data is chosen depending on the information that the Gaussian classifier should model.

13. System according to claim 1, wherein in classifying whether the received audio data is genuine or a spoof a compensation term depending on the particular application is used.

14. Method for classifying whether audio data received in a speaker recognition system is genuine or a spoof using a Gaussian classifier.

15. Computer-readable medium comprising computer-readable instructions that, when executed on a computer, are adapted to carry out a method according to claim 14.