Detection of replay attack
A method of detecting a replay attack comprises: receiving an audio signal representing speech; identifying speech content present in at least a portion of the audio signal; obtaining information about a frequency spectrum of each portion of the audio signal for which speech content is identified; and, for each portion of the audio signal for which speech content is identified: retrieving information about an expected frequency spectrum of the audio signal; comparing the frequency spectrum of portions of the audio signal for which speech content is identified with the respective expected frequency spectrum; and determining that the audio signal may result from a replay attack if a measure of a difference between the frequency spectrum of the portions of the audio signal for which speech content is identified and the respective expected frequency spectrum exceeds a threshold level.
1. A method of detecting a replay attack, the method comprising:
receiving an audio signal representing speech;
identifying speech content present in at least a portion of the audio signal;
obtaining information about a frequency spectrum of each portion of the audio signal for which speech content is identified;
for each portion of the audio signal for which speech content is identified, retrieving information about an expected frequency spectrum of the audio signal;
comparing the frequency spectrum of portions of the audio signal for which speech content is identified with the respective expected frequency spectrum in one of a frequency band of 20-200 Hz and an ultrasonic frequency band; and
determining that the audio signal results from a replay attack if a measure of a difference between the frequency spectrum of the portions of the audio signal for which speech content is identified and the respective expected frequency spectrum exceeds a threshold level.
2. A method according to claim 1 , comprising:
removing effects of a channel and/or noise from the received audio signal; and
using the audio signal after removing the effects of the channel and/or noise when obtaining the information about the frequency spectrum of each portion of the audio signal for which speech content is identified.
3. A method according to claim 1 , wherein identifying speech content present in at least a portion of the audio signal comprises identifying at least one test acoustic class.
4. A method according to claim 3 , wherein the at least one test acoustic class comprises one or more specific phonemes.
5. A method according to claim 4 , wherein the at least one test acoustic class comprises fricatives.
6. A method according to claim 5 , wherein the at least one test acoustic class comprises sibilants.
7. A method according to claim 4 , wherein the at least one test acoustic class comprises plosives.
8. A method according to claim 3 , wherein identifying at least one test acoustic class comprises identifying a location of occurrences of the test acoustic class in known speech content.
9. A method according to claim 8 , wherein the known speech content comprises a pass phrase.
10. A method according to claim 1 , wherein comparing the frequency spectrum of portions of the audio signal for which speech content is identified with the respective expected frequency spectrum comprises:
comparing the frequency spectrum of portions of the audio signal for which speech content is identified with the respective expected frequency spectrum in a frequency band in the range of 5-20 kHz.
11. A method according to claim 1 , wherein comparing the identified parts of the audio signal with the respective retrieved information for the corresponding test acoustic class comprises:
comparing a power level in at least one frequency band of the identified parts of the audio signal with a power level in at least one corresponding frequency band of the expected spectrum of the audio signal.
12. A method according to claim 11 , wherein the measure of the difference between the identified parts of the audio signal and the respective retrieved information for the corresponding test acoustic class comprises a difference in power of greater than 1 dB.
13. A method according to claim 1 , further comprising:
performing a speaker identification process on the received audio signal; and
for each test acoustic class, retrieving information about an expected spectrum of the audio signal for a speaker identified by said speaker identification process.
14. A system for detecting a replay attack, the system comprising:
an input, for receiving an audio signal representing speech; and
a processor, wherein the processor is configured for:
identifying speech content present in at least a portion of the audio signal;
obtaining information about a frequency spectrum of each portion of the audio signal for which speech content is identified;
for each portion of the audio signal for which speech content is identified, retrieving information about an expected frequency spectrum of the audio signal;
comparing the frequency spectrum of portions of the audio signal for which speech content is identified with the respective expected frequency spectrum in one of a frequency band of 20-200 Hz and an ultrasonic frequency band; and
determining that the audio signal results from a replay attack if a measure of a difference between the frequency spectrum of the portions of the audio signal for which speech content is identified and the respective expected frequency spectrum exceeds a threshold level.
15. A device comprising a system as claimed in claim 14 , wherein the device comprises one of: a smartphone, a tablet or laptop computer, a games console, a home control system, a home entertainment system, an in-vehicle entertainment system, or a domestic appliance.
16. A computer program product, comprising a non-transitory computer-readable medium, storing code for causing a suitable programmed processor to perform a method as claimed in claim 1 .