Bioacoustic authentication

Abstract

According to various but not all embodiments, an apparatus is provided that includes means for performing the following operations: determining at least two locations of a user touching a device; selecting a first location and a second location from the at least two locations to define a transmission path of an acoustic signal through the user; applying the acoustic signal through the first location to the user; detecting the acoustic signal transmitted through the user at the second location; and analyzing the detected acoustic signal to determine whether it indicates transmission of the applied acoustic signal through an authorized user based on a known bioacoustic signature of the authorized user.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to bioacoustic authentication. Some embodiments relate to bioacoustic authentication by transmitting an acoustic signal between a device and a user's hand at a location where a touch contact is established. BACKGROUND

[0002] Authentication methods require a user to perform an action to provide a credential to verify their identity. Multi-factor authentication methods require a user to perform multiple actions. These actions are typically unrelated to the task the user wishes to engage with. SUMMARY

[0003] According to various but not all embodiments, there is provided an apparatus comprising means for determining at least two locations at which a user touches a device; selecting a first location and a second location from among the at least two locations to define a transmission path of an acoustic signal through the user; applying the acoustic signal to the user through the first location; detecting the acoustic signal transmitted through the user at the second location; analyzing the detected acoustic signal to determine whether it is indicative of transmission of the applied acoustic signal through an authorized user based on a known bioacoustic signature of the authorized user.

[0004] According to various but not all embodiments, there is provided a method comprising determining at least two locations at which a user touches a device; selecting a first location and a second location from among the at least two locations to define a transmission path of an acoustic signal through the user; applying the acoustic signal to the user through the first location; detecting the acoustic signal transmitted through the user at the second location; analyzing the detected acoustic signal to determine whether it is indicative of transmission of the applied acoustic signal through an authorized user based on a known bioacoustic signature of the authorized user.

[0005] According to various but not all embodiments, there is provided a computer program which when run on a computer performs: determining at least two locations at which a user touches a device; selecting a first location and a second location from among the at least two locations to define a transmission path of an acoustic signal through the user; applying the acoustic signal to the user through the first location; detecting the acoustic signal transmitted through the user at the second location; analyzing the detected acoustic signal to determine whether it is indicative of transmission of the applied acoustic signal through an authorized user based on a known bioacoustic signature of the authorized user.

[0006] According to various but not all embodiments, there is provided an example as claimed in the appended claims.

[0007] The scope of protection sought for various embodiments of the present invention is defined by the appended claims. Embodiments and features described in the specification that are not within the scope of the claims if any, are intended to be examples of useful examples of various embodiments of the invention.

[0008] The following section of the “SUMMARY” describes various features that can be features of any of the embodiments described in the preceding section of the “SUMMARY.” Furthermore, descriptions of functions should be considered as also disclosing any means for accomplishing the function.

[0009] For the at least two touch locations, a portion of a hand of the user providing the touch contact can be determined.

[0010] Selecting the first location and the second location can include, for the acoustic signal, identifying available transmission paths through the user between the portion of the hand of the user providing the touch contact; and selecting one of the available transmission paths.

[0011] Selecting one of the available transmission paths can be based on an authentication confidence score associated with the available transmission path.

[0012] Selecting the first location can be conditioned on the first location being a location at which localized vibrations can be controlled to produce the target acoustic signal.

[0013] Selecting the second location can be conditioned on the second location being a location at which localized vibrations can be measured.

[0014] The applied acoustic signal can be adapted for the defined transmission path.

[0015] The applied acoustic signal can be adapted based on one or more touch characteristics at the first and / or second locations.

[0016] Analyzing the detected acoustic signal can include processing the detected acoustic signal to extract a transfer function of the transmission path; and determining whether the extracted transfer function corresponds to a known bioacoustic signature of an authorized user.

[0017] Controlling access to the at least one application can depend on whether the detected acoustic signal indicates transmission of the applied acoustic signal by the authorized user.

[0018] Guidance can be provided to the user indicating where the user should touch the device based on which of the possible transmission paths have the highest associated authentication confidence scores.

[0019] A gesture of the user touching the device at the at least two locations can be determined. The selection of the first location and the second location can be conditioned on the gesture corresponding to a predefined gesture for the user.

[0020] Applying the acoustic signal to the user through the first location can include causing a plurality of movable elements of an actuator or a plurality of actuators to vibrate a panel forming at least a portion of a display or a housing of the device such that the superposition of the vibrations at the first location produces the acoustic signal.BRIEF DESCRIPTION OF DRAWINGS BRIEF DESCRIPTION OF DRAWINGS

[0021] Some examples will now be described with reference to the drawings, in which:

[0022] Figure 1 An example apparatus is shown;

[0023] Figure 2 An example method is shown;

[0024] Figure 3 Another example method is shown;

[0025] Figures 4A to 4D An example implementation of the disclosure is shown. DETAILED DESCRIPTION

[0026] Examples of the disclosure relate to an apparatus 101 which can be configured to authenticate that a user of a device 401 is an authorised user. This is achieved by applying an acoustic signal to the user such that the signal is transmitted through the user and back to the device 401.

[0027] The acoustic signal is transmitted along paths formed by the user's skeleton. The acoustic transmission characteristics of these paths are influenced by, for example, the structure, size and weight of the skeleton. Thus, individuals can be distinguished by a bioacoustic signature which reflects their unique skeletal structure.

[0028] By using the acoustic signal transmitted through the user to authenticate the user, the identity of the user can be verified as they begin or continue to use the device 401 for a task in which they wish to participate. There can be no need for a separate, task-unrelated user action to establish their credentials.

[0029] Figure 1 An apparatus 101 according to examples of the disclosure is schematically illustrated. Figure 1 The apparatus 101 illustrated in

[0030] In the example of Figure 1 The apparatus 101 comprises a controller 103. The controller 103 can be implemented as controller circuitry. The controller 103 can be implemented in pure hardware, can have certain aspects in pure software including firmware, or can be a combination of hardware and software including firmware.

[0031] As shown in Figure 1 The controller 103 can be implemented using instructions enabling hardware functionality, for example by using executable instructions of a computer program 109 in a general purpose or special purpose processor 105, which can be stored on a computer readable storage medium (disk, memory etc) to be executed by such a processor 105.

[0032] The processor 105 is configured to read from and write to the memory 107. The processor 105 can also include an output interface and an input interface, wherein data and / or commands are output by the processor 105 via the output interface, and data and / or commands are input to the processor 105 via the input interface.

[0033] The memory 107 stores a computer program 109 comprising computer program instructions (computer program code 111) which, when loaded into the processor 105, control the operation of the apparatus 101. The computer program instructions of the computer program 109 provide the means by which the apparatus 101 is enabled to perform the methods 201, 301, and optionally perform the logic and routines as illustrated. Figure 2 The processor 105 is configured to read from and write to the memory 107. The processor 105 can also include an output interface and an input interface, wherein data and / or commands are output by the processor 105 via the output interface, and data and / or commands are input to the processor 105 via the input interface. Figure 3 The processor 105 is configured to read from and write to the memory 107. The processor 105 can also include an output interface and an input interface, wherein data and / or commands are output by the processor 105 via the output interface, and data and / or commands are input to the processor 105 via the input interface.

[0034] The apparatus 101 therefore comprises: at least one processor 105; and at least one memory 107 including computer program code 111, the at least one memory 107 and the computer program code being configured to, with the at least one processor 105, cause the apparatus 101 at least to perform: determining 203 at least two locations at which a user touches the device 401; selecting 205 a first location 407 and a second location 409 from the at least two locations to define a transmission path 411 of an acoustic signal through the user; applying 207 the acoustic signal to the user through the first location 407; detecting 209 the acoustic signal transmitted through the user at the second location 409; and analysing 211 the detected acoustic signal to determine whether it indicates that the applied acoustic signal was transmitted through an authorised user based on a known bioacoustic signature of the authorised user.

[0035] As Figure 1 The computer program 109 can arrive at the apparatus 101 via any suitable delivery mechanism 113, as illustrated. The delivery mechanism 113 can be, for example, a machine readable medium, a computer readable medium, a non-transitory computer readable storage medium, a computer program product, a memory device, a record medium such as a compact disc read-only memory (CD-ROM) or digital versatile disc (DVD), an article of manufacture that includes or embodies a computer program 109, a data signal in which the computer program 109 is embodied, or a data stream on which the computer program 109 is embodied. The delivery mechanism can be a signal configured to reliably transfer the computer program 109. The apparatus 101 can propagate the computer program 109 as a computer data signal on a carrier. In some examples, the computer program 109 can use a wireless protocol such as Bluetooth, Bluetooth Low Energy, Bluetooth Smart, 6LoWPan (IPv6 over Low power Personal Area Networks), ZigBee, ANT+, Near Field Communication (NFC), Radio Frequency Identification, Wireless Local Area Network (Wireless LAN), or any other suitable protocol.

[0036] In some examples, computer program instructions are provided for causing the apparatus 101 to perform at least the following: determining 203 at least two locations at which a user touches the device 401 ; selecting 205 a first location 407 and a second location 409 from the at least two locations to define a transmission path 411 of an acoustic signal through the user; applying 207 the acoustic signal to the user through the first location 407; detecting 209 the acoustic signal transmitted through the user at the second location 409; and analysing 211 the detected acoustic signal to determine whether it indicates that the applied acoustic signal was transmitted through an authorised user based on a known bioacoustic signature of the authorised user.

[0037] The computer program instructions can be included in a computer program 109, a non-transitory computer-readable medium, a computer program product, a machine-readable medium. In some but not all examples, the computer program instructions can be distributed over more than one computer program 109.

[0038] Although the memory 107 is illustrated as a single component / circuit, it can be implemented as one or more separate components / circuits, some or all of which can be integrated / removable and / or can provide persistent / semi-persistent / dynamic / cached storage.

[0039] Although the processor 105 is illustrated as a single component / circuit, it can be implemented as one or more separate components / circuits, some or all of which can be integrated / removable. The processor 105 can be a single core or multicore processor.

[0040] References to ‘computer-readable storage medium’, ‘computer program product’, ‘tangibly embodied computer program’ etc., or a ‘controller’, ‘computer’, ‘processor’ etc. should be understood to encompass not only computers having different architectures such as single / multi-processor architectures and sequential (Von Neumann) / parallel architectures but also specialized circuits such as FPGAs, ASICs, signal processing devices and other processing circuitry. References to ‘computer program’, ‘instructions’ ‘code’ etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-functionality device, gate array or programmable logic device etc.

[0041] As used in this application, the term ‘circuitry’ can refer to one or more or all of the following:

[0042] (a) hardware-only circuitry implementations (such as implementations in only analog and / or digital circuitry),

[0043] (b) combinations of hardware circuits and software, such as (as applicable):

[0044] (i) combinations of analog and / or digital hardware circuit(s) with software / firmware and

[0045] (ii) any portions of hardware processor(s) with software (including digital signal processors) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions and

[0046] (c) hardware circuit(s) that requires software (e.g., firmware) for operation, but software is not required for the hardware circuit(s) to operate. For example, a processor can require software for operations, but it is not required for the processor to operate.

[0047] The definition of this circuit applies to all uses of this term in this application including any claims. As a further example, as used in this application, the term "circuit" would also cover an implementation in pure hardware circuitry or

[0048] Figure 2 The illustrated blocks and in some examples Figure 3 The illustrated blocks can represent steps of a method, and / or code segments in a computer program 109. The illustration of a particular order to the blocks does not necessarily imply that the order is required or preferred, as the blocks can be varied in sequence and arrangement, and some blocks can be omitted. Further, some blocks can be performed in parallel.

[0049] Figure 2 An example method 201 is shown that can be implemented by an apparatus 101 as shown in Figure 1 The example method 201 is an authentication method 201.

[0050] The method 201 includes, at block 203, determining at least two locations of a user touching a device 401.

[0051] Determining locations of a user touching a device 401 ("touch locations") can be achieved by touch screen technology that detects touch locations, such as capacitive sensing, resistive sensing, surface acoustic wave sensing, optical sensing, and other suitable ways.

[0052] Touch locations on portions of the device 401 other than a touch screen can also be determined.

[0053] For the panels 403, 405 of the device 401, which can be vibrated in a manner that acoustically actuates different locations on the panels 403, 405 as desired, e.g., by creating standing waves from the vibration of the panels 403, 405 with displacement antinodes at different locations, different locations can be acoustically actuated and responses can be measured. A weakened response indicates a touch contact at the location that was acoustically actuated.

[0054] Gesture modeling based on one or more touch characteristics, such as the location, pressure, angle, and shape of a touch on the touchscreen, can be used to predict other touch locations that can not be on the touchscreen.

[0055] In some examples, guidance can be provided to the user that indicates where the user should touch the device 401 based on which of the possible transmission paths 411 have the highest associated authentication confidence scores.

[0056] It should be appreciated that the possible transmission paths 411 are not necessarily limited to those that have already been established to exist, but can also include putative transmission paths 411, e.g., based on anatomical likelihoods of the user's hand 413 given the shape and size of the device 401.

[0057] The authentication confidence score associated with a transmission path 411 indicates the probability of a correct authentication when using that path 411 as a biometric. The higher the authentication confidence score, the lower the probability of a false authentication. The authentication confidence score can reflect both uniqueness and repeatability characteristics. Uniqueness is a measure of how distinguishable the acoustic transmission characteristics of the path 411 are from other known characteristics. Repeatability is a measure of how susceptible the acoustic transmission characteristics of the path 411 are to other factors.

[0058] The guidance can also indicate which part of the user's hand 413 should be used to touch the device 401.

[0059] The guidance can be provided by a UI output of the device 401, such as a visual display or a sound instruction.

[0060] As an illustrative example, the user can be guided by the guidance to place a finger on an existing microphone housing on the device 401, as that touch location can enable more sensitive measurements of acoustic signals transmitted from the user to the device 401. As another illustrative example, the user can be guided by the guidance to place a finger on a haptic button on the device 401, as that touch location can cause strongly localized acoustic signals to be transmitted from the device 401 to the user.

[0061] In some examples in which the device 401 is transformable between different geometric configurations, such as in the case of a sliding or flip phone, guidance can also be provided to the user. The user can be directed to transform the device 401 into a certain geometric configuration prior to implementing the authentication method 201. Certain configurations can provide a higher likelihood of a transmission path 411 than possible in other configurations, associated with a higher authentication confidence score.

[0062] At block 205, the method 201 includes selecting a first location 407 and a second location 409 from the at least two locations to define a transmission path 411 of the acoustic signal through the user.

[0063] In some examples, for the at least two touch locations, a portion of the hand 413 of the user providing the touch contact is determined. The portion of the hand can be identified in terms of the closest bone.

[0064] To determine the portion of the hand 413 of the user providing the touch contact, the device 401 can employ an under-screen fingerprint reader to identify which finger provided the touch contact at the different touch locations.

[0065] The portion of the hand 413 of the user providing the touch contact can also be determined based on one or more characteristics of the touch contact (“touch characteristics”). The one or more touch characteristics can be detected at one or more of the at least two locations at which the user touches the device 401. The touch characteristics can include, for example, a pressure, an angle, a shape of the touch contact. From the pressure, angle, and shape, and the location, a probability of different gestures can be determined. This can be implemented using a machine learning algorithm trained via supervised learning, for example, using training data in which input touch pressure, angle, shape, and location data is labeled according to a known corresponding gesture. Based on the most likely gesture, the portion of the hand 413 of the user providing the touch contact can be predicted.

[0066] The gesture can also be determined using a capacitive sensor configured to provide information indicative of a profile of an object (the hand 413) proximate to the device 401 based on the electrical conductivity of the object compared to the electrical conductivity of air (or its relative lack thereof). The profile can be matched to a known gesture. Again, based on the most likely gesture, the portion of the hand 413 of the user providing the touch contact can be predicted.

[0067] In some examples, the selection of the first location 407 and the second location 409 can be made conditional on the determined gesture of the user touching the device 401 at at least two locations corresponding to a predefined gesture for the user. The user can set the predefined gesture or can be notified of what gesture the predefined gesture is set to. Thus, the predefined gesture is a knowledge factor. Since the bioacoustic signature is an intrinsic factor, multi-factor authentication is achieved without requiring multiple actions by the user.

[0068] In some examples, for the acoustic signal, an available transmission path 411 through the user between the parts of the user's hand 413 providing the touch contact can be identified. The identification of the available transmission path 411 is determined from the parts of the user's hand 413 providing the touch contact.

[0069] In this example, the selection of the first location 407 and the second location 409 includes selecting one of the available transmission paths 411.

[0070] In the case where only two touch locations are determined, there are two available transmission paths 411 - one from a first part of the user's hand 413 to a second part of the user's hand 413 and one from the second part of the user's hand 413 to the first part of the user's hand 413. As an illustrative example, the first part can be the knuckle 417 and the second part can be the corresponding fingertip 415. The knuckle 417 is effectively a junction point for two different bone conduction paths - one into the metacarpal bone and one into the phalange bone. In contrast, the fingertip 415 provides only one bone conduction path - into the phalange bone. Thus, an acoustic signal applied to the knuckle 417 is more likely to be dissipated into a bone conduction path that does not reconnect with the device 401. As a result, if an acoustic signal is applied to the knuckle 417 rather than the fingertip 415, the detected acoustic signal can be weaker. Thus, selecting a touch location corresponding to the fingertip 415 as the first location 407 can result in a detected acoustic signal with a better signal-to-noise ratio, thus supporting a higher degree of confidence in authentication based on the detected signal.

[0071] The selection of one of the available transmission paths 411 can be based on an authentication confidence score associated with the available transmission path 411.

[0072] The authentication confidence score can include a fixed component and an optional variable component.

[0073] The fixed component can be specific to the identity of the transmission path 411.

[0074] The variable component can be responsive to one or more touch characteristics, such as the pressure, angle and shape of the touch - all of which can affect the transmission of the acoustic signal through the interface between the device 401 and the user.

[0075] Where there are more than two touch locations to choose from, the variable component may also depend on the feasibility of reducing or preventing vibration from being propagated from the device 401 to the user at touch locations that do not form part of the selected transmission path 411. For example, in the case of a touch position 411, the vibration is transmitted to the user by forming an acoustic standing wave (with the displacement antinode at the first location 407) on the panels 403, 405 of the device 401 (as described below with respect to FIG. Figures 4A to 4D In the case where the acoustic signal is applied to the user (as described in more detail) to prevent vibrations from propagating into the user at other touch locations on the same panel 403, 405, the standing wave should have displacement nodes at these other touch locations. Reducing or preventing vibrations from propagating into the user from the device 401 at touch locations that do not form part of the selected transmission path 411 means that multiple acoustic signals are not transmitted through the user to the second location 409 along different transmission paths 411. This can reduce the challenge of determining whether the detected signal indicates a transmission via the authenticated user.

[0076] In some examples, selecting first position 407 and second position 409 may be based solely on these variable components without requiring specific identification of available transmission paths 411. As a result, in some examples, the portion of the user's hand 413 providing the touch contact may not be determined.

[0077] Thus, in some examples, selecting the first position 407 and the second position 409 includes detecting one or more touch characteristics at one or more of at least two positions where the user touches the device 401, and then selecting those positions as the first and second positions 407, 409 where the touch characteristics provide minimal transformation (such as attenuation or frequency shift) of the acoustic signal passing through the interface between the device 401 and the user.

[0078] Therefore, in some examples, selecting the first position 407 and the second position 409 includes selecting a touch position as the first position 407 that can provide an acoustic signal while generating no vibration or relatively small vibration at other touch positions.

[0079] In some examples, selection of first position 407 is conditional on first position 407 being a position where local vibration can be controlled to generate a target acoustic signal. If the target acoustic signal cannot be generated at the touch position, then the touch position may not be selected as first position 407. For example, the options for first position 407 may be limited to those positions on panels 403, 405 of device 401 where displacement antinodes of standing waves can be formed from vibrations of panels 403, 405.

[0080] In some examples, selecting the second location 409 is conditioned on the second location 409 being a location where local vibrations can be measured.

[0081] The first and second locations 407, 409 are different locations. The selection of the first and second locations 407, 409 is a selection of two different locations.

[0082] At block 207, the method 201 includes applying an acoustic signal to the user through the first location 407.

[0083] In some examples, the applied acoustic signal is adapted for the defined transmission path 411, which can have been identified from a portion of the user's hand 413 providing the touch contact.

[0084] The transmission path adapted acoustic signal can be obtained by a computation or measurement of a unique and distinctive signature acoustic signal that will best highlight the acoustic transmission characteristics of the path 411, such as described below in relation to the calibration method 301. Figure 3

[0085] In some examples, the applied acoustic signal is adapted based on one or more touch characteristics at the first and / or second locations 407, 409.

[0086] Adapting the acoustic signal to be applied based on one or more touch characteristics can include applying a transformation that takes into account at least in part the effects of touch location, pressure, angle, shape variations. Alternatively, the acoustic signal can be looked up from a target acoustic signal record indexed by the identified transmission path 411, touch location, pressure, angle, and shape.

[0087] In some examples, the acoustic signal to be applied can be determined by selecting a base signal adapted for a stored transmission path 411 closest to the defined transmission path 411 and then applying a transformation to the base signal that takes into account at least in part the differences between the closest stored transmission path 411 and the defined transmission path 411.

[0088] Rather than adapting the acoustic signal to be applied based on the environment such as the defined transmission path 411 or touch characteristics, a new acoustic signal can be applied. This can provide greater security as there is no recorded response that can be played back to spoof the authentication method 201, however, the authentication confidence score can be reduced as the new acoustic signal will not be adapted to the environment.

[0089] It will be appreciated that the applied acoustic signal can be neither adapted to the environment nor new.

[0090] At block 209, the method 201 includes detecting the acoustic signal transmitted through the user and back to the device 401 at the second location 409. The detection is of the acoustic signal transformed by the transmission through the user along the defined transmission path 411. ​

[0091] At block 211, the method 201 comprises analysing the detected acoustic signal to determine whether it is indicative of the applied acoustic signal being transmitted by an authorised user. Determining whether the detected acoustic signal is indicative of the applied acoustic signal being transmitted by an authorised user can be based on a known bioacoustic signature of the authorised user.

[0092] The bioacoustic signature can be recorded explicitly, such as in the form of a transfer function, or implicitly, such as in the form of an input-output pair, a stimulus-response pair.

[0093] Depending on whether the detected acoustic signal is indicative of the applied acoustic signal being transmitted by an authorised user, access to at least one application can be controlled. The at least one application can be a function or set of functions that the device 401 is configured to perform or enable. For example, the application can be online credit and debit card transactions.

[0094] In some examples, the detected acoustic signal is processed to extract a transfer function of the transmission path 411. The extracted transfer function can be compared to a known bioacoustic signature of the authorised user using correlation, pattern recognition or any other suitable process.

[0095] Alternatively, the detected acoustic signal can be compared to a recorded response to a stimulus that matches the applied acoustic signal, in particular a recorded response associated with transmission via the defined transmission path 411.

[0096] If the comparison shows a good match or correlation, then access to the at least one application can be permitted.

[0097] If the comparison does not show a good match or correlation, then access to the at least one application can be denied. In some examples, the user can be provided with an alert that access is denied. The user can be provided with guidance to indicate that the user should change the position at which the device 401 is being touched.

[0098] The authentication method 201 described above in relation to Figure 2 The authentication method 201 described above in relation to

[0099] Figure 3 An example method 301 is shown that can be implemented by an apparatus 101 as shown in Figure 1 The example method 301 is a calibration method 301.

[0100] The calibration method 301 can have a number of purposes.

[0101] One purpose of the calibration method 301 is to obtain at least one bioacoustic signature of a user to be designated as an authorized user. Multiple bioacoustic signatures of the user can be obtained for different transmission paths 411 through the user, thus enabling the authentication method 201 to be performed with fewer restrictions on how the user can touch the device 401.

[0102] At block 303, the calibration method 301 comprises instructing the user to touch the device 401 simultaneously at at least two locations.

[0103] In some examples, the at least two locations can be specific to the user. In other examples, the at least two locations are freely chosen by the user. In some examples, if the device 401 is handheld, the user can be instructed to hold the device 401 in a way that feels natural for ordinary use.

[0104] At block 305, the calibration method 301 comprises transmitting at least one acoustic signal through the user between one or more pairs of the at least two locations.

[0105] At block 307, the calibration method 301 comprises obtaining at least one bioacoustic signature of the user from the acoustic signals transmitted back to the device 401 from the user.

[0106] The calibration method 301 can further comprise instructing the user to change the location at which the device 401 is touched. In some examples, if the device 401 is handheld, the user can be instructed to change their grip on the device 401 to another grip that feels natural for ordinary use.

[0107] After the touch location has been changed, blocks 305 and 307 can be repeated for the new touch location.

[0108] A further optional purpose of the calibration can be to identify the transmission paths 411 provided by the user touching the device 401, and to determine and record authentication confidence scores associated with the identified transmission paths 411. These scores can be used when selecting the first and second locations 407, 409 at block 205 of the authentication method 201.

[0109] The identification of the transmission paths 411 can be achieved by determining which parts of the user’s hand 413 provide the touch contact in the manner described above.

[0110] A further optional purpose of the calibration can be to determine how to adapt the acoustic signals to be applied to the user for different ones of the identified transmission paths 411.

[0111] To this end, different acoustic signals can be transmitted along each transmission path 411, for example by transmitting a chirp signal to the user. The acoustic signals can be determined that best emphasize the unique and distinctive features of the acoustic transmission characteristics of each path 411.

[0112] Figures 4A to 4D An example implementation of the present disclosure is shown. The implementation comprises a device 401, such as a mobile phone or any other suitable type of device, such as other computing or communication devices and other handheld computing or communication devices.

[0113] The device 401 can comprise an apparatus 101 as shown. Figure 1

[0114] The device 401 comprises panels 403, 405 forming at least part of a display or a housing of the device 401 and at least one actuator (not shown) configured to apply a force to the panels 403, 405 to cause vibrations of the panels 403, 405. In some examples, multiple actuators are configured to apply a force to the same panel 403, 405. In some examples, the actuator configured to apply a force to the panels 403, 405 comprises multiple movable elements, each movable element being able to apply a different force to the panels 403, 405.

[0115] Two such panels 403, 405 can be provided on different sides of the device 401, for example on a front face as shown and a back face as shown. The panel 403 on the front face of the device 401 can form at least part of a display and the panel 403 on the back face of the device 401 can form part of a housing. Providing front and back panels 403, 405 that can enable acoustic signals to be applied and detected in accordance with blocks 207 and 209 of the authentication method 201 can enable the authentication method 201 to be performed when the user is holding the device 401 in a natural manner. Figure 4A Figure 4D

[0116] It will be appreciated that the device 401 can comprise more than two such panels 403, 405.

[0117] Applying an acoustic signal to the user at the first location 407 in accordance with block 207 of the authentication method 201 can comprise causing multiple actuators or multiple movable elements of an actuator to vibrate the panels 403, 405 such that the superposition of the vibrations at the first location 407 results in the acoustic signal. Adjusting the frequency and phase of the actuators or movable elements of the actuator creates different excitation patterns on the panels 403, 405.

[0118] ​​​Detecting acoustic signals transmitted through the user comprises measuring forces applied to the plurality of actuators or to the plurality of movable elements of the actuator by vibrations of the panel 403, 405 caused at the second location 409 by transmission of acoustic signals from the user to the panel 403, 405.

[0119] There can be a time delay between applying acoustic signals and detecting acoustic signals. Therefore, the first and second locations 407, 409 can be on the same panel 403, 405 of the device 401 and the acoustic signals transmitted from the user to the panel 403, 405 can be detected at the second location 409 by time-gating the electrical signal(s) associated with the actuator. Alternatively, the device 401 can comprise a plurality of such panels 403, 405 and the first and second locations 407, 409 can be on different panels 403, 405, thus not requiring time-gating.

[0120] In the example implementation of Figure 4A , the display panel 403 is vibrated in a manner that produces target acoustic signals at the locations where the user's fingertips 415 touch the display panel 403. Acoustic signals are transmitted into the user via their fingertips 415. The acoustic signals are transmitted from the fingertips 415 along the paths 411 in each finger that are in contact with the display panel 403 to the knuckles 417, as shown on the palm side of the user's hand 413 in Figure 4B and on the back side of the user's hand 413 in Figure 4C . On the palm side, the knuckles 417 are in contact with the rear housing panel 405 of the device 401, as shown in Figure 4D . Acoustic signals that have been transmitted along the user's fingers are at least partially transmitted from the knuckles 417 to the rear housing panel 405, enabling these signals to be transmitted through the user to be detected. Analysis of these detected acoustic signals reveals whether the user is authorised to use the device 401 to access at least one application.

[0121] As can be seen from this example implementation, examples of the present disclosure are not limited to transmitting acoustic signals through a user via one transmission path 411 at a time, but can transmit acoustic signals through a user via different transmission paths 411 at the same time. In this case, the selection of the first and second locations 407, 409 of block 205 of the authentication method 201 is performed for multiple pairs of first and second locations 407, 409 to define multiple transmission paths 411.

[0122] While the examples described herein primarily refer to the user's fingers, fingertips and fingerprints, it will be appreciated that other parts of the user's hand 413, such as the user's thumbs, can also be used to provide touch contact at a touch location on a part of the device 401, form part of a transmission path 411 and / or be scanned by a fingerprint reader of the device 401.

[0123] Where structural features have been described, they can be replaced by components for performing the function or functions of that structural feature, whether that function or those functions are described explicitly or implicitly.

[0124] Thus, in some examples, the apparatus 101 comprises means for: determining 203 at least two locations at which a user touches the device 401; selecting 205 a first location 407 and a second location 409 from the at least two locations to define a transmission path 411 of an acoustic signal through the user; applying 207 the acoustic signal through the first location 407 to the user; detecting 209 the acoustic signal transmitted through the user at the second location 409; and analysing 211 the detected acoustic signal to determine whether it indicates that the applied acoustic signal was transmitted through an authorised user based on a known bioacoustic signature of the authorised user.

[0125] In some, but not all, examples, the apparatus 101 is configured to transfer data from the apparatus 101 with or without storing the data locally in a memory 107 at the apparatus 101 and with or without processing the data locally by a circuit or processor 105 at the apparatus 101.

[0126] The data can be, for example: the detected acoustic signal of block 209 of the authentication method 201; the bioacoustic signature obtained via the calibration method 301; the identity of the transmission path 411 and the associated authentication confidence score also obtained via the calibration method 301; and the transmission path-adapted acoustic signal also obtained via the calibration method 301.

[0127] The data can be stored remotely at one or more devices, in processed or unprocessed format. The data can be stored in the cloud.

[0128] The data can be processed remotely at one or more devices. The data can be processed partly locally and partly remotely at one or more devices.

[0129] The data can be transferred wirelessly to remote devices via short-range radio communication, such as Wi-Fi or Bluetooth, or by long-range cellular radio link. The apparatus can comprise a communication interface, such as a radio transceiver for data communication, for example.

[0130] The apparatus 101 can be part of the Internet of Things, forming part of a larger distributed network.

[0131] The processing of the data, whether local or remote, can be for health monitoring, data aggregation, patient care, vital sign monitoring, or other purposes.

[0132] The processing of data, whether local or remote, can involve artificial intelligence or machine learning algorithms. The data can for example be used as a learning input to train a machine learning network or can be used as a query input to a machine learning network that provides an answer. The machine learning network can for example use linear regression, logistic regression, vector support machines or non-recurrent machine learning networks such as single or multiple hidden layer neural networks.

[0133] The processing of data, whether local or remote, can produce an output. The output can be communicated to the apparatus 101 where it can produce an output perceptible to a subject, such as an audio output, a visual output or a haptic output.

[0134] The data record can comprise only temporary records, or can comprise permanent records, or can comprise both temporary records and permanent records. Temporary records mean that the data is recorded temporarily. Permanent records mean that the data is in the form of an addressable data structure that is retrievable from an addressable storage space and thus can be stored and retrieved until deleted or overwritten, although long-term storage can or can not occur.

[0135] The apparatus, method and computer program can use machine learning, which can include statistical learning. Machine learning is a field of computer science that endows computers with the ability to learn without being explicitly programmed. A computer learns from experience E with respect to some task T and some performance measure P, whether it improves its performance at T (as measured by P) as a result of experience E. The computer can typically learn from previous training data to make predictions on future data. Machine learning includes fully or partially supervised learning and fully or partially unsupervised learning. It can implement discrete outputs (e.g. classification, clustering) and continuous outputs (e.g. regression). Machine learning can for example be implemented using different methods such as cost function minimization, artificial neural networks, support vector machines and Bayesian networks. Cost function minimization can for example be used in linear and polynomial regression as well as K-means clustering. Artificial neural networks (e.g. with one or more hidden layers) model complex relationships between input vectors and output vectors. Support vector machines can be used for supervised learning. Bayesian networks are directed acyclic graphs representing conditional independencies of multiple random variables.

[0136] The term "comprising" as used herein has an inclusive, rather than an exclusive, meaning. That is, any reference to "comprising" indicates that the referred to element can comprise one or more of the referred to elements. If it is intended to use "comprising" in an exclusive sense, it will be explicitly stated as, for example, "comprising only one of".

[0137] In this description, reference has been made to various examples. The description of features or functions in relation to an example indicates that the features or functions are present in that example. Use of the term “example” or “for example” or “may” or “might” in the text denotes, whether explicitly stated or not, that such features or functions are present in at least the described example, whether described as an example or not, and they can be, but are not necessarily, present in some or all other examples. Thus “example”, “for example”, “may” or “might” refers to a particular instance in a class of examples. A characteristic of an instance can be a characteristic of only that instance or a characteristic of the class or a characteristic of a subclass of the class, where the subclass includes some but not all of the instances of the class. Thus, features described with reference to one example but not with reference to another are implicitly disclosed as possible combinations, as far as possible, in other examples but do not necessarily have to be used in that other example.

[0138] Although examples have been described in the preceding paragraphs with reference to various examples, it should be understood that modifications can be made to the given examples without departing from the scope of the claims.

[0139] Features described in the preceding description can be used in combinations other than the combinations explicitly described above.

[0140] Although functions have been described with reference to certain features, those functions can be executable by other features whether or not described.

[0141] Although features have been described with reference to certain examples, those features can also be present in other examples whether or not described.

[0142] The term “a” or “the” has an inclusive, not an exclusive, meaning in this document. That is, any reference to “X includes a / the Y” means that X can include only one Y or can include more than one Y unless the context clearly indicates otherwise. If it is intended to use “a” or “the” with an exclusive meaning, then it will be explicitly stated in the context. In some cases, the use of “at least one” or “one or more” can be used to emphasize the inclusive meaning, but the absence of these terms should not be taken to infer any exclusive meaning.

[0143] The presence of a feature (or combination of features) in a claim has the meaning of that feature or combination of features itself, and also the meaning of a feature (equivalent feature) that achieves substantially the same technical effect. Equivalent features include, for example, variant features and achieve substantially the same result in substantially the same way. Equivalent features include, for example, features that perform substantially the same function in substantially the same way to achieve substantially the same results.

[0144] In this description, reference has been made to various examples using adjectives or adjectival phrases to describe example features. Such description of features in relation to examples indicates that the feature is present in some examples exactly as described and substantially as described in other examples.

[0145] While efforts have been made to accentuate those features which are considered to be important, it should be understood that the applicant can seek protection for any patentable feature or combination of features mentioned above and / or shown in the drawings, whether or not it has been emphasized.

Claims

1. A device for bioacoustic authentication, comprising: at least one processor; as well as at least one memory storing computer program code; The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to: Determining at least two locations where the user touched the device; selecting a first position and a second position from the at least two positions to define a transmission path of the acoustic signal through the user; applying an acoustic signal to the user via the first location; detecting, at the second location, an acoustic signal transmitted through the user; analyzing the detected acoustic signal to determine whether it indicates transmission of the applied acoustic signal through the authorized user based on a known bioacoustic signature of the authorized user; as well as for the at least two touch locations, determining which parts of the user's hand provided the touch contact; Wherein selecting the first position and the second position comprises: for the acoustic signal, identifying available transmission paths through the user between the portion of the user's hand providing the touch contact; and selecting one of the available transmission paths.

2. The device according to claim 1, wherein Selecting one of the available transmission paths is based on an authentication confidence score associated with the available transmission path.

3. The device according to claim 1, wherein The first position is selected on the condition that the first position is a position where local vibration can be controlled to generate a target acoustic signal.

4. The device according to claim 1, wherein The second position is selected on the condition that the second position is a position where local vibration can be measured.

5. The device according to claim 1, wherein The applied acoustic signal is adapted to the defined transmission path.

6. The device according to claim 1, wherein The applied acoustic signal is adapted based on one or more touch characteristics at the first location and / or the second location.

7. The device according to claim 1, wherein Analyzing the detected acoustic signal includes processing the detected acoustic signal to extract a transfer function of the transmission path; and determining whether the extracted transfer function corresponds to the known bioacoustic signature of the authorized user.

8. The device according to claim 1, wherein The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to: Access to at least one application is controlled depending on whether the detected acoustic signal indicates transmission of the applied acoustic signal by an authorized user.

9. The device according to claim 1, wherein The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to: Guidance is enabled to be provided to the user indicating where the user should touch the device based on which possible transmission paths have the highest associated authentication confidence scores.

10. The device according to claim 1, wherein The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to: A gesture of the user when touching the device at the at least two locations is determined, and wherein selection of the first location and the second location is conditional on the gesture corresponding to a predefined gesture for the user.

11. The device according to claim 1, wherein Applying the acoustic signal to the user through the first location comprises causing multiple movable elements of an actuator or multiple actuators to vibrate a panel forming at least part of a display or housing of the device so that the superposition of vibrations at the first location produces the acoustic signal.

12. A method for bioacoustic authentication, comprising: Determining at least two locations where the user touched the device; selecting a first position and a second position from the at least two positions to define a transmission path of the acoustic signal through the user; applying an acoustic signal to the user via the first location; detecting, at the second location, an acoustic signal transmitted through the user; analyzing the detected acoustic signal to determine whether it indicates transmission of the applied acoustic signal through the authorized user based on a known bioacoustic signature of the authorized user; as well as for the at least two touch locations, determining which parts of the user's hand provided the touch contact; Wherein selecting the first position and the second position comprises: for the acoustic signal, identifying available transmission paths through the user between the portion of the user's hand providing the touch contact; and selecting one of the available transmission paths.

13. The method according to claim 12, further comprising: Guidance is enabled to be provided to the user indicating where the user should touch the device based on which possible transmission paths have the highest associated authentication confidence scores.

14. The method according to claim 12, further comprising: determining a gesture of the user touching the device at the at least two locations, And wherein the selection of the first position and the second position is conditional on the gesture corresponding to a predefined gesture for the user.

15. A non-transitory computer-readable medium comprising program instructions stored thereon for performing at least the following operations: Determining at least two locations where the user touched the device; selecting a first position and a second position from the at least two positions to define a transmission path of the acoustic signal through the user; applying an acoustic signal to the user via the first location; detecting, at the second location, an acoustic signal transmitted through the user; analyzing the detected acoustic signal to determine whether it indicates transmission of the applied acoustic signal through the authorized user based on a known bioacoustic signature of the authorized user; as well as for the at least two touch locations, determining which parts of the user's hand provided the touch contact; Wherein selecting the first position and the second position comprises: for the acoustic signal, identifying available transmission paths through the user between the portion of the user's hand providing the touch contact; and selecting one of the available transmission paths.

16. The non-transitory computer-readable medium of claim 15, further comprising program instructions stored thereon for performing at least the following operations: Guidance is enabled to be provided to the user indicating where the user should touch the device based on which possible transmission paths have the highest associated authentication confidence scores.

Images