Abstract: There is described a system and method for performing biometric authentication, preferably voice biometric authentication. The system has a host device such as a mobile phone and a coupled headset device. The headset device is arranged to receive audio, and to cryptographically protect the audio before transmission to the host device for verification and biometric authentication.

Abstract: This application relates to Class D amplifier circuits. A modulator controls a Class D output stage based on a modulator input signal (Dm) to generate an output signal (Vout) which is representative of an input signal (Din). An error block, which may comprise an ADC, generates an error signal (?) from the output signal and the input signal. In various embodiments the extent to which the error signal (?) contributes to the modulator input signal (Dm) is variable based on an indication of the amplitude of the input signal (Din). The error signal may be received at a first input of a signal selector block. The input signal may be received at a second input of the signal selector block. The signal selector block may be operable in first and second modes of operation, wherein in the first mode the modulator input signal is based at least in part on the error signal; and in the second mode the modulator input signal is based on the digital input signal and is independent of the error signal.

Abstract: Embodiments of the invention relate to methods, apparatus and systems for biometric processes. The methods include updating stored ear model data for a user following successful authentication of the user. The ear model data may be acquired using a personal audio device that generates an acoustic stimulus and detects a measured response. The acquisition of the ear model data may be responsive to a determination that the personal audio device is inserted into or placed adjacent to the user's ear. The acquisition of the ear model data may also be responsive to the determination that the personal audio device has not been removed from or moved away from the user's ear.

Abstract: The present disclosure relates to Class D amplifier circuitry comprising: an input for receiving an input signal; first and second output nodes for driving a load connected between the first and second output nodes. A first driver stage is provided for switching the first node between a first supply rail and a second supply rail, and a second driver stage is provided for switching the second node between the first supply rail and the second supply rail. The Class D amplifier circuitry also includes first driver control circuitry configured to receive a first carrier wave and control the switching of the first driver stage based in part on the first carrier wave; second driver control circuitry configured to receive a second carrier wave and control the switching of the second driver stage based in part on the second carrier wave; and a carrier wave generator configured to provide the first carrier wave and the second carrier wave.

Abstract: 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.

Abstract: There is described a two-terminal multi-level memristor element synthesised from binary memristors, which is configured to implement a variable resistance based on unary or binary code words. There is further described a circuit such as a synapse circuit implemented using a multi-level memristor element.

Abstract: A biometric is formed for at least one enrolled speaker by: obtaining a sample of speech of the enrolled speaker; obtaining a measure of a fundamental frequency of the speech of the enrolled speaker in each of a plurality of speech frames; and forming a first distribution function of the fundamental frequency of the speech of the enrolled speaker. Subsequently, for a speaker to be recognised, a sample of speech of the speaker to be recognised is obtained. Then, a measure of a fundamental frequency of the speech of the speaker to be recognised is obtained in each of a plurality of speech frames. A second distribution function of the fundamental frequency of the speech of the speaker to be recognised is formed, the second distribution function and the first distribution function are compared, and it is determined whether the speaker to be recognised is the enrolled speaker based on a result of comparing the second distribution function and the first distribution function.

Abstract: A method of speaker identification, comprises: receiving an audio signal representing speech; removing effects of a channel and/or noise from the received audio signal to obtain a cleaned audio signal; obtaining an average spectrum of at least a part of the cleaned audio signal; and comparing the average spectrum with a long term average speaker model for an enrolled speaker. Based on the comparison, it can be determined whether the speech is the speech of the enrolled speaker.

Abstract: A method of determining whether a sound has been generated by a loudspeaker comprises receiving an audio signal representing at least a part of the sound. The audio signal is separated into different frequency bands. The signal content of different frequency bands are compared. Based on said comparison, frequency-based variations in signal content indicative of use of a loudspeaker are identified.

Abstract: Detecting a replay attack on a voice biometrics system comprises receiving a speech signal; forming an autocorrelation of at least a part of the speech signal; and identifying that the received speech signal may result from a replay attack based on said autocorrelation. Identifying that the received speech signal may result from a replay attack may be achieved by: comparing the autocorrelation with a reference value; and identifying that the received speech signal may result from a replay attack based on a result of the comparison of the autocorrelation with the reference value, or by: supplying the autocorrelation to a neural network trained to distinguish autocorrelations formed from speech signals resulting from replay attacks from autocorrelations formed from speech signals not resulting from replay attacks.

Abstract: Embodiments of the invention relate to methods, apparatus and systems for biometric processes. The methods include updating stored ear model data for a user following successful authentication of the user. The ear model data may be acquired using a personal audio device that generates an acoustic stimulus and detects a measured response. The acquisition of the ear model data may be responsive to a determination that the personal audio device is inserted into or placed adjacent to the user's ear. The acquisition of the ear model data may also be responsive to the determination that the personal audio device has not been removed from or moved away from the user's ear.

Abstract: Embodiments of the disclosure relate to methods, apparatus and systems for biometric processes. The invention relates to initiating generation of an acoustic stimulus for application to a user's ear and extracting features for use in a biometric process from a measured response signal. The measured response signal may be used to derive one or more quality metrics and the quality metrics may be used to validate features extracted from the measured response. The quality metrics may be used to provide feedback to the user seeking to carry out the biometric process.

Abstract: Detecting a replay attack on a voice biometrics system comprises receiving a speech signal; forming an autocorrelation of at least a part of the speech signal; and identifying that the received speech signal may result from a replay attack based on said autocorrelation. Identifying that the received speech signal may result from a replay attack may be achieved by: comparing the autocorrelation with a reference value; and identifying that the received speech signal may result from a replay attack based on a result of the comparison of the autocorrelation with the reference value, or by: supplying the autocorrelation to a neural network trained to distinguish autocorrelations formed from speech signals resulting from replay attacks from autocorrelations formed from speech signals not resulting from replay attacks.

Abstract: A method of speaker recognition comprises: receiving an audio signal comprising speech; performing a biometric process on a first part of the audio signal, wherein the first part of the audio signal extends over a first time period; obtaining a speaker recognition score from the biometric process for the first part of the audio signal; performing a biometric process on a plurality of second parts of the audio signal, wherein the second parts of the audio signal are successive sections of the first part of the audio signal, and wherein each second part of the audio signal extends over a second time period and the second time period is shorter than the first time period; obtaining a respective speaker recognition score from the biometric process for each second part of the audio signal; and determining whether there has been a speaker change based on the respective speaker recognition scores for successive second parts of the audio signal.

Abstract: This application relates to sensing circuits for sensing a physical property or quantity of interest. The sensing circuit has an oscillator comprising a hysteretic comparator and a loop filter configured to output an oscillation signal. The loop filter comprises a first component with an electrical property that varies with the physical property or quantity of interest. A time constant of the loop filter depends on the electrical property of the first component. A decoder is configured to receive the oscillation signal and provide an indication of any change in frequency of the oscillation signal as an indication of a change in the physical property or quantity of interest. The electrical property may be an impedance, such as a resistance.

Abstract: The present invention relates to methods, apparatus and systems for authentication of a user based on ear biometric data, and voice biometric data or other authentication data. The ear biometric data may be combined with voice biometric data or with a security question and response.

Abstract: A method of speaker verification comprises: comparing a test input against a model of a user's speech obtained during a process of enrolling the user; obtaining a first score from comparing the test input against the model of the user's speech; comparing the test input against a first plurality of models of speech obtained from a first plurality of other speakers respectively; obtaining a plurality of cohort scores from comparing the test input against the plurality of models of speech obtained from a plurality of other speakers; obtaining statistics describing the plurality of cohort scores; modifying said statistics to obtain adjusted statistics; normalising the first score using the adjusted statistics to obtain a normalised score; and using the normalised score for speaker verification.

Abstract: Detecting liveness of a speaker comprises: generating an ultrasound signal; receiving an audio signal comprising a reflection of the ultrasound signal; using the received audio signal comprising the reflection of the ultrasound signal to detect the liveness of a speaker; monitoring ambient ultrasound noise; and adjusting the operation of a system receiving the audio signal, based on a level of the reflected ultrasound and the monitored ambient ultrasound noise. The method can be used in a voice biometrics system, in which case detecting the liveness of a speaker comprises determining whether a received speech signal may be a product of a replay attack. The operation of the voice biometrics system may be adjusted based on a level of the reflected ultrasound and the monitored ambient ultrasound noise.

Abstract: This application relates to microphone authentication apparatus for verifying whether or not an audio signal originated at a microphone (101, 102). The microphone authentication apparatus (300) has a comparison block (301) configured to receive a first signal (A*) indicative of one or more spectral parameters of at least part of an audio signal to be verified, and compare the one or more spectral parameters to one or more predetermined characteristic microphone parameters relating to a characteristic resonance associated with an acoustic port of a microphone. The first signal (A*) may be an audio signal (A) and the microphone authentication apparatus may have a feature extract module (303) for determining the spectral parameters. Based on the comparison determination block (304) may whether the audio signal originated from a microphone and may send a verification signal (VMIC) to a voice biometric module 111.

Abstract: Embodiments of the disclosure provide a mechanism for performing a biometric algorithm on ear biometric data acquired from a user. The mechanism may be used for biometric authentication, or in-ear detect, for example. In one embodiment, a method is provided in which a quality metric of an input signal to a transducer and/or a signal on a return path from the transducer is monitored. One or more steps of a biometric process, comprising monitoring of a parameter related to an admittance of the transducer, comparison of the parameter to a stored profile for an authorised user, generation of a score based on the comparison, comparison of the score to one or more threshold values, and initiation of one or more actions, may be performed responsive to the quality metric meeting one or more criteria.