Detection of replay attack
In order to detect a replay attack in a speaker recognition system, at least one feature is identified in a detected magnetic field. It is then determined whether the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker. If so, it is determined that a replay attack may have taken place.
1. A method of detecting a replay attack in a speaker recognition system, the method comprising:
identifying at least one feature of a detected magnetic field;
determining whether the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker; and
if so, determining that a replay attack may have taken place,
wherein the step of identifying at least one feature of the detected magnetic field comprises:
receiving a signal from a magnetometer; and
detecting modulation of the at least one feature from the received signal from the magnetometer; and
wherein the step of determining whether the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker comprises:
determining whether a degree of the modulation of the at least one feature at a syllabic rate is indicative of playback of speech through the loudspeaker.
2. A method as claimed in claim 1 , further comprising:
receiving an audio signal representing speech, wherein the audio signal is received at substantially the same time as the magnetic field is detected; and
if it is determined that the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker, determining that the audio signal may result from said replay attack.
3. A method as claimed in claim 1 , wherein the step of identifying at least one feature of the detected magnetic field comprises:
receiving a signal from a magnetometer; and
performing a Discrete Fourier Transform on the received signal from the magnetometer.
4. A method as claimed in claim 1 , comprising determining whether a detected pattern of variability of the magnetic field is indicative of a reference pattern associated with playback of a predetermined spoken phrase through a loudspeaker.
5. A method as claimed in claim 4 , wherein determining whether the detected pattern of variability of the magnetic field is indicative of a reference pattern associated with playback of a predetermined spoken phrase through a loudspeaker comprises:
comparing the detected pattern of variability of the magnetic field with a stored reference pattern.
6. A method as claimed in claim 5 , wherein the stored reference pattern corresponds to the predetermined spoken phrase, as spoken by a specific enrolled user.
7. A method as claimed in claim 5 , wherein the stored reference pattern corresponds to the predetermined spoken phrase, as spoken by multiple speakers.
8. A method as claimed in claim 4 , wherein determining whether the detected pattern of variability of the magnetic field is indicative of a reference pattern associated with playback of a predetermined spoken phrase through a loudspeaker comprises:
passing the detected pattern of variability of the magnetic field to a classifier that has been trained to with inputs obtained from playback of the predetermined spoken phrase through a loudspeaker.
9. A non-transitory computer readable storage medium having computer-executable instructions stored thereon that, when executed by processor circuitry, cause the processor circuitry to perform a method according to claim 1 .
10. A system for detecting a replay attack in a speaker recognition system, the system comprising:
a detector for identifying at least one feature of a detected magnetic field; and
a processor for: determining whether the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker; and, if so, determining that a replay attack may have taken place,
wherein the detector is configured for:
receiving a signal from a magnetometer; and
detecting modulation of the at least one feature from the received signal from the magnetometer; and
wherein the step of determining whether the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker comprises:
determining whether a degree of the modulation of the at least one feature at a syllabic rate is indicative of playback of speech through the loudspeaker.
11. A system as claimed in claim 10 , further configured for:
receiving an audio signal representing speech, wherein the audio signal is received at substantially the same time as the magnetic field is detected; and
if it is determined that the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker, determining that the audio signal may result from said replay attack.
12. A system as claimed in claim 10 , configured for identifying at least one feature of the detected magnetic field by:
receiving a signal from a magnetometer; and
performing a Discrete Fourier Transform on the received signal from the magnetometer.
13. A system as claimed in claim 10 , configured for determining whether a detected pattern of variability of the magnetic field is indicative of a reference pattern associated with playback of a predetermined spoken phrase through a loudspeaker.
14. A system as claimed in claim 13 , configured for determining whether the deteted pattern of variability of the magnetic field is indicative of a reference pattern associated with playback of a predetermined spoken phrase through a loudspeaker by:
comparing the detected pattern of variability of the magnetic field with a stored reference pattern.
15. A system as claimed in claim 14 , wherein the stored reference pattern corresponds to the predetermined spoken phrase, as spoken by a specific enrolled user.
16. A system as claimed in claim 14 , wherein the stored reference pattern corresponds to the predetermined spoken phrase, as spoken by multiple speakers.
17. A system as claimed in claim 13 , configured for determining whether the detected pattern of variability of the magnetic field is indicative of a reference pattern associated with playback of a predetermined spoken phrase through a loudspeaker by:
passing the detected pattern of variability of the magnetic field to a classifier that has been trained to with inputs obtained from playback of the predetermined spoken phrase through a loudspeaker.
18. A device comprising a system as claimed in claim 10 .
19. A device as claimed in claim 18 , wherein the device comprises a mobile telephone, an audio player, a video player, a mobile computing platform, a games device, a remote controller device, a toy, a machine, or a home automation controller or a domestic appliance.