Authentication device
A method of authenticating a speech signal in a first device comprises receiving a speech signal, and performing a live speech detection process to determine whether the received signal represents live speech. The live speech detection process generates a live speech detection output. A certificate is formed by encrypting at least the live speech detection output. The received signal, and the certificate, are transmitted to a separate second device.
1. A method of authenticating a speech signal in a first device, the method comprising:
receiving a speech signal;
performing a live speech detection process to determine whether the received signal represents live speech, wherein the live speech detection process generates a live speech detection output;
forming a certificate by encrypting at least a quality metric of the received signal with the live speech detection output, wherein the quality metric of the received signal comprises a fundamental frequency of speech in the received signal; and
transmitting the received signal and the certificate to a separate second device.
2. The method according to claim 1 , further comprising:
forming a hash of the received signal; and comprising:
forming the certificate by encrypting the hash of the received signal with the live speech detection output.
3. The method according to claim 1 , comprising:
receiving the speech signal with a first sample rate;
performing the live speech detection process using the received speech signal with the first sample rate;
decimating the received signal to a second sample rate; and
transmitting the received signal to the separate second device with the second sample rate.
4. The method according to claim 3 , wherein the first sample rate is higher than 16 kHz and the second sample rate is 16 kHz.
5. The method according to claim 1 , wherein the live speech detection process generates the live speech detection output in the form of a score value having at least two possible values.
6. The method according to claim 1 , wherein the quality metric of the received signal comprises a signal-noise ratio of the received signal.
7. The method according to claim 1 , further comprising:
transmitting a device specific identifier to the separate second device.
8. The method according to claim 7 , further comprising forming the certificate by encrypting said device specific identifier with the live speech detection output.
9. A device comprising:
an input for receiving a speech signal; and
a processor for performing a live speech detection process to determine whether the received signal represents live speech, wherein the live speech detection process generates a live speech detection output; and for forming a certificate by encrypting at least a quality metric of the received signal with the live speech detection output, wherein the quality metric of the received signal comprises a fundamental frequency of speech in the received signal; and
an output configured for transmitting the received signal and the certificate to a separate second device.
10. The device according to claim 9 , wherein the output is configured for transmitting the received signal and the certificate to the separate second device, wherein the device and the separate second device are located in a single host device.
11. The device according to claim 9 , wherein the device comprises a first integrated circuit, and the separate second device comprises a second integrated circuit located within the same host device as the first integrated circuit.