In-vehicle privacy system, method for masking speech and vehicle comprising an in-vehicle privacy system

Abstract

In-vehicle privacy system comprising: Audio output means (146, 147) associated with a first zone (110) of a vehicle (100); Audio source means (250) for sending an audio signal (205) to the audio output means (146, 147); Speech intelligibility means (310) for estimating speech intelligibility in the first zone (110); Control means (200) arranged to control one or more properties of the audio signal (205) in dependence on the speech intelligibility estimate in order to mask the speech of a second occupant in a second zone (150) of the interior of the vehicle from a first occupant in the first zone (110); wherein the speech intelligibility means (310) is arranged to receive data on one or more parameters of the vehicle and to estimate the speech intelligibility in dependence thereon; wherein the one or more parameters comprise one or more of vehicle speed, drive motor speed, and engine speed.

Description

FIELD OF THE INVENTION

[0001] The present disclosure relates to an apparatus and method, and more particularly, but not exclusively, to an apparatus and method for enhancing privacy within a vehicle. Inventive aspects relate to a system, a method, a vehicle, and computer software. STATE OF THE ART

[0002] In some cases, it is desirable to provide privacy between the occupants of a vehicle. For example, if an occupant of a vehicle wishes to make a telephone call, at least that occupant may prefer that the call be conducted privately. Even if the occupant makes the call using a headset or similar device, their speech may still be audible to the other occupants of the vehicle. Physical barriers in vehicles, such as those between the occupants in the front seats and those in the rear seats of the vehicle, are well known. However, these are intrusive and at least partially separate the occupants permanently, even if the barrier can be partially removed, for example, lowered.Alternatively, the volume of an in-vehicle entertainment system can be increased to mask speech, but this may not be desirable for the occupant making the call and for other occupants. In this context, reference is made to documents DE 10 2014 210 760 B4, DE 10 2014 214 053 A1, and DE 10 2014 214 052 A1.

[0003] It is an object of embodiments of the invention to at least mitigate one or more problems of the prior art. SUMMARY OF THE INVENTION

[0004] Aspects and embodiments of the invention provide an in-vehicle privacy system, an in-vehicle privacy system controller, a method for masking speech in a vehicle, a vehicle, and computer software as claimed in the appended claims.

[0005] According to one aspect of the present invention, a system is provided comprising audio source means for providing an audio signal to an audio output means, speech intelligibility means for estimating speech intelligibility in a first zone of an interior of a vehicle, and control means for controlling one or more properties of the audio signal in dependence on the speech intelligibility estimate. Advantageously, the properties or features of the audio are controlled in dependence on speech intelligibility to mask speech.

[0006] According to one aspect of the invention, there is provided an in-vehicle privacy system comprising: audio output means associated with a first zone of an interior of a vehicle, audio source means for providing an audio signal to the audio output means, speech intelligibility means for estimating speech intelligibility in the first zone, and control means arranged to control one or more characteristics of the audio signal in dependence on the speech intelligibility estimate to mask the speech of a second occupant in a second zone of the interior of the vehicle from a first occupant in the first zone. Advantageously, the features or characteristics of the audio signal are controlled in dependence on the speech intelligibility to mask the speech of the second occupant.

[0007] System as described above, where: the audio output means comprises one or more audio output devices; the audio source means comprises an audio signal generator device; the speech intelligibility means comprises a processor arranged to determine the speech intelligibility estimate; and the control means comprises a processor arranged to control one or more properties of the audio signal.

[0008] The one or more properties of the audio signal may include a frequency profile of the audio signal. Advantageously, the frequency profile is used to mask speech.

[0009] Optionally, the audio source means comprises a noise source. Advantageously, the noise source may be effective in masking speech. The noise source may be a Brownian (red), white, or pink noise source. A suitable noise source for masking speech may advantageously be used.

[0010] The audio source means may comprise an audio source. Optionally, the audio is provided by a music source, a radio source, or a streaming source. Advantageously, the audio may be pleasing to a listener.

[0011] The speech intelligibility means may be arranged to receive a signal from an audio input means arranged in the first zone and to estimate speech intelligibility in dependence thereon. Advantageously, speech intelligibility is determined based on audio in the first zone.

[0012] The speech intelligibility means is arranged to receive data indicative of one or more parameters of the vehicle and to estimate speech intelligibility in dependence thereon. Advantageously, the one or more parameters are used to estimate speech intelligibility, which can reduce the complexity of the estimation. The one or more parameters comprise one or more of vehicle speed, drive motor speed, and engine speed.

[0013] Optionally, the speech intelligibility estimate is an articulation index (AI). Advantageously, the index provides a unit for the estimation.

[0014] The audio output means associated with the first zone may comprise one or more audio output means arranged in the first zone of the vehicle interior. Advantageously, the audio is output to the first zone.

[0015] The one or more audio output means may be arranged in a headrest of a seat in the first zone. Advantageously, the audio is output close to the occupant's ears.

[0016] The control means may be arranged to control the one or more properties of the audio signal to reduce the speech intelligibility estimate. Advantageously, the speech is masked by the audio signal.

[0017] According to one aspect of the invention, a controller for an in-vehicle privacy system is provided, the controller comprising input means for receiving a speech intelligibility signal indicative of speech intelligibility in a first zone of an interior of a vehicle, control means arranged to control one or more properties of an audio signal in dependence on the speech intelligibility signal, and output means for causing the audio signal to be output in the first zone to mask the speech of a second occupant in a second zone of the vehicle interior from a first occupant in the first zone.

[0018] Control device as previously described, wherein: the input means comprises an electrical input for receiving the speech intelligibility signal; the control means comprises a processor arranged to control the one or more properties of an audio signal; and the output means comprises an electrical output for outputting the audio signal.

[0019] The input means may be configured to receive the speech intelligibility signal from an audio input means arranged in the first zone. The control means may be configured to control the one or more properties of the audio signal in dependence thereon.

[0020] The control means is optionally arranged to receive data indicative of one or more parameters of the vehicle and to control the one or more properties of the audio signal in dependence thereon.

[0021] The speech intelligibility signal may indicate an articulation index (AI).

[0022] The one or more properties of the audio signal may include a frequency profile of the audio signal.

[0023] One or more properties of the audio signal can be controlled to reduce the estimate of speech intelligibility.

[0024] The audio signal may include a representation of a noise signal. Optionally, the noise signal is Brownian, white, or pink noise.

[0025] According to one aspect of the invention, a method for masking speech in a vehicle is provided, comprising estimating speech intelligibility in a first zone of an interior of a vehicle, controlling one or more properties of an audio signal in dependence on the estimation of speech intelligibility, and outputting the audio signal in the first zone to mask the speech of a second occupant in a second zone of the vehicle interior from a first occupant in the first zone.

[0026] Estimating speech intelligibility may comprise receiving an audio signal from the first zone of the vehicle interior and estimating speech intelligibility in dependence thereon.

[0027] Estimating speech intelligibility may include receiving data indicative of one or more parameters of the vehicle and estimating speech intelligibility in dependence thereon.

[0028] The one or more parameters may include one or more of vehicle speed, drive motor speed, and engine speed.

[0029] The estimation of speech intelligibility can be an articulation index (AI).

[0030] One or more properties of the audio signal can be controlled to reduce the estimate of speech intelligibility.

[0031] Controlling one or more properties of the audio signal may include controlling a frequency distribution of the audio signal.

[0032] The audio signal may include a representation of a noise signal. Optionally, the noise signal is Brownian, white, or pink noise.

[0033] The audio signal is optionally output to mask speech of a second occupant in a second zone of the vehicle's interior from a driver of the vehicle.

[0034] The method may include determining a head position of an occupant. The occupant may be the first occupant in the first zone. The method may include determining one or more properties of an audio signal depending on the head position. The one or more properties may be a distribution of the audio signal among multiple audio output means. Advantageously, the audio may be output according to the head position to improve masking.

[0035] According to one aspect of the invention, computer software is provided which, when executed by a computer, is arranged to carry out a method according to one aspect of the invention. The computer software may be stored on a computer-readable medium. The computer software may be tangibly stored on a computer-readable medium. The computer software may be stored on a non-transient computer-readable medium.

[0036] According to one aspect of the invention, a vehicle is provided comprising: an in-vehicle privacy system according to one aspect of the invention, a control device according to one aspect of the invention arranged to carry out a method according to one aspect of the invention, or comprising computer software according to one aspect of the invention.

[0037] Within the scope of this application, it is expressly intended that the various aspects, embodiments, examples, and alternatives presented in the preceding paragraphs, in the claims, and / or in the following description and drawings, and in particular their individual features, may be considered independently of one another or in any combination. This means that all embodiments and / or features of any embodiment may be combined in any manner and / or combination, provided these features are not incompatible.The applicant reserves the right to amend any originally filed claim or to file any new claim accordingly, including the right to amend any originally filed claim to depend on and / or incorporate any feature of any other claim not previously claimed in that manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] One or more embodiments of the invention will now be described, by way of example only, with reference to the accompanying drawings, in which: Fig. 1 a vehicle according to an embodiment of the invention; Fig. 2 is an illustration of a system according to an embodiment of the invention; Fig. 3 an illustration of a control device according to an embodiment of the invention; and Fig. 4 a method according to an embodiment of the invention. DETAILED DESCRIPTION

[0039] Fig. 1 schematically shows a vehicle 100 according to an embodiment of the invention. The vehicle 100 includes a plurality of seating positions 120, 140, 160, 180. Four seating positions are shown in a two-by-two arrangement; however, it should be noted that this is only an example and that other numbers of seating positions, such as five seating positions, as well as those in other arrangements, are conceivable. Each seating position 120, 140, 160, 180 is associated with a corresponding seat for an occupant of the vehicle 100.

[0040] The first and second seats 120, 140 are front seats of the vehicle 100, while the third and fourth seats 160, 180 are rear seats of the vehicle 100. The second and third seats 140, 160 are depicted as being associated with a respective zone 110, 150 of the vehicle, which may be designated as an infotainment zone. Each zone of the vehicle may be a subset or portion of the interior of the vehicle 100. It is desirable for audio content in one zone to be isolated or restricted to that zone. In particular, it is desirable for audio content provided in one zone 150 to be prevented from being intelligible in another zone 110.

[0041] As in Fig. 1, the vehicle 100 includes two zones, namely a first zone 110 and a second zone 150. The vehicle 100 may include other numbers of zones, such as three or four zones. However, a description is provided as an example with reference to the two zones illustrated, although the invention is not limited in this regard. The first zone 110 is associated with an occupant in a front seat of the vehicle 100, who may be a driver of the vehicle 100 in a right-hand drive configuration of the vehicle 100. The second zone 150 is associated with an occupant in a rear seat of the vehicle 100, hereinafter referred to as a passenger. In an example where the vehicle 100 is driven by a driver, such as a chauffeur, the rear seat occupant may make (incoming and outgoing) calls while traveling in the vehicle 100, although the invention is not limited in this regard.The passenger can answer the calls either via a handheld handset or via a hands-free car system of the vehicle 100, as will be explained. It is desirable that at least the passenger's speech be unintelligible to the driver of the vehicle 100. It may also be desirable to prevent the speech of another person not in the vehicle 100 from being intelligible to the driver. While embodiments of the invention are described with reference to the passenger and the driver of the vehicle, it should be understood that the teachings of the invention can be applied between any two occupants of the vehicle in different zones. Furthermore, it is desirable to prevent speech between occupants of different zones 110, 150 from being intelligible without a physical barrier or without creating excessive noise in the vehicle.

[0042] The first zone 110 is associated with audio output means 146, 147. The second zone is associated with audio output means 166, 167. The audio output means 146, 147, 166, 167 are arranged to output audio primarily to one occupant in each respective zone 110, 150. The audio output means 146, 147 of the first zone 110 is arranged to output different audio, in use, than the audio output means 166, 167 of the second zone 150. In some embodiments, the audio output means 146, 147, 166, 167 are arranged in a headrest of each seat 140, 160 to output audio directly to the ears of the seat occupant, thereby assisting in the audio isolation of each zone 110, 150. However, other installation locations for the audio output means 146, 147, 166, 167 are also provided, such as inside the seat body or behind the interior paneling of the vehicle 100.It should be noted that the audio output means 146, 147, 166, 167 may each be a loudspeaker for outputting audible audio based on received electrical signals.

[0043] In some embodiments, the first zone 110 is associated with an audio input means 130. The audio input means 130 is provided for outputting an electrical signal indicative of audio in the first zone 110. The audio input means may be a first microphone 130. The first microphone may be used to determine audible features of the first zone 110. In other embodiments, however, the microphone 130 may not be included, and audible features of the first zone 110 may be inferred, as explained later. In the illustrated embodiment, the second zone 150 includes an audio input means 170. The audio input means 170 is provided for outputting an electrical signal indicative of audio in the second zone 150. The audio input means may be a second microphone 170. The second microphone 170 may be used to support a telephone conversation with the passenger in the second zone 150.In some embodiments, the second microphone is used to determine one or more features of speech in the second zone 150. The one or more features may be a frequency profile and a loudness of the speech in the second zone 150.

[0044] In some embodiments, a head position determining means 135 is provided with respect to at least one seating position. In the Fig. 1, a head position determining means 135 is provided relative to the second seating position 140 for determining a position of the head of the occupant of the first zone 110, as will be explained later. The head position determining means 135 may consist of one or more cameras or imaging devices arranged in the vehicle 100. In the example shown in Fig. 1, the one or more cameras are arranged to provide image data corresponding to an image of one or more occupants from whom the system is arranged to mask speech within the vehicle, which in the example of Fig. 1 is the occupant of the first zone 110.

[0045] The vehicle 100 further comprises a control means 200, which may be embodied as a control device 200. The control means 200 may be communicatively coupled to the first microphone 130 and / or the audio output means 146, 147. In some embodiments, the control means 200 is communicatively coupled to the head position determining means 135, as explained later. Some embodiments may include alternative or additional communicable connections to the control means 200, as explained later.

[0046] Fig. 2 shows a system according to an embodiment of the invention. The system 200 comprises a control means 200 in the form of a control device 200 according to an embodiment of the invention. The control device is an in-vehicle privacy control device 200 according to an embodiment of the invention. The control device 200 is arranged to at least partially render speech within the vehicle 100 outside of one or more zones in the vehicle 100 to which the control device 200 is linked unintelligible.

[0047] The control device 200 may be implemented as an electronic device including one or more processors operable to execute computer software instructions that may be stored in a memory accessible to one or more processors, such as a storage device of the control device 200. The control device 200 may be communicatively coupled to a communication bus 210 of the vehicle 100 to exchange, i.e., send and / or receive, data with other units or modules communicatively coupled to the communication bus 210. The communication bus 210 may be implemented, for example, by a communication network such as CAN bus, Ethernet, or Flexray, although other bus protocols are also conceivable.In some embodiments, the controller 200 receives vehicle information via the communication bus 210 from a vehicle system 260 indicating one or more characteristics of the vehicle 100, such as vehicle speed and / or drive motor or engine speed, e.g., in revolutions per minute (RPM).

[0048] The system further comprises audio output means 146, 147 associated with at least one zone, which in the illustrated embodiment is the first zone 110. It should be noted that the control device 200 may be associated with audio output means of more than one zone. The control device 200 is arranged, in use, to cause the audio output means 146, 147 to output audible signals having one or more features intended to render speech outside the first zone 110 at least partially unintelligible. The control device 200 comprises output means, which may be provided in the form of an electrical output, associated with the audio output means 146, 147, each of which may be a loudspeaker.

[0049] In some embodiments, as previously stated, the system further comprises a first audio input means 130 for outputting a signal to the control device 200 indicative of audible signals in the first zone 110. The audio input means 130 may be a microphone located in the first zone 110. The control device 200 comprises an input means, such as an electrical input, for receiving an electrical signal from the microphone 130.

[0050] The system further comprises an audio source means 250 for providing an audio signal 205. The audio source means is coupled to the control device 200 through an electrical input of the controller for receiving the audio signal 205. In some embodiments, the audio source means 250 comprises a noise source. The noise source may be a Brownian (red), white, or pink noise source. The audio source means 250 may be an audio source device for sending the audio signal 205 to the control device. In other embodiments, the audio signal 205 is received from an audio source, which may be provided by a music source, a radio or streaming audio source, or a combination thereof.The audio source may be a vehicle entertainment system capable of receiving radio, digitally streamed music or audio (such as audiobooks), for example, via the Internet, or playing stored audio, for example, from a CD, DVD, storage device, or other storage medium.

[0051] As mentioned above, in some embodiments, the system includes the head position determining means 135 for determining the position of the head of the occupant of the first zone 110. As mentioned above, the occupant of the first zone 110 may be in the Fig. 1, a driver of the vehicle 100.

[0052] Furthermore, in some embodiments, the system includes a second audio input means 170 disposed in the second zone 150. The second audio input means 170 may provide the control device 200 with a signal indicative of one or more characteristics of an occupant in the second zone 150, ie, the front passenger of the vehicle 100.

[0053] Fig. Figure 3 illustrates modules operatively executed on the control device 200 according to an embodiment of the invention. The modules may be implemented as software executed by the one or more processing means of the control device 200.

[0054] A speech intelligibility module (SIM) 310 is provided for estimating speech intelligibility in one or more zones of the vehicle 100. In particular, in the example of Fig. 1, the SIM 310 is arranged to estimate the intelligibility of speech within the first zone 110. The speech may be that of an occupant in another zone of the vehicle, such as the second zone 150 in the example of Fig. 1. That is, the SIM 310 operatively determines whether the speech of the occupant in the second zone 150 is intelligible in the first zone 110. In one embodiment, the SIM 310 receives the signal from the microphone 130 to determine the audio characteristics in the first zone 110. In some embodiments, the SIM 310 may alternatively or additionally receive vehicle information such as speed, prime mover, or engine speed to estimate the intelligibility of the speech in the first zone 110.

[0055] A masking module (MM) 320 is provided for operatively controlling one or more properties of an audio output signal. The MM 320 is arranged to control the one or more properties depending on the speech intelligibility estimate provided by the SIM 310. The audio output signal is controlled such that the speech of a second occupant in the second zone 150 of the interior of the vehicle 100 is masked from a first occupant in the first zone 110 of the interior of the vehicle 100. The audio signal whose properties are controlled by the MM 320 is the audio signal 205 provided by the audio source 250. The audio output signal is provided to the audio output means 146, 147 associated with the first zone 110.

[0056] Referring again to SIM 310, in some embodiments, SIM 310 receives the signal from microphone 130 indicating sound in first zone 110. SIM 310 is arranged to estimate speech intelligibility in first zone 110 in dependence thereon. The speech intelligibility estimate may be an articulation index (AI). AI is an acoustic index used to estimate or predict the speech recognition ability of a person hearing speech. SIM 310 may determine AI based on the signal from microphone 130. SIM 310 operates by dividing a predetermined frequency spectrum into multiple bands, for example, 20 bands, although other numbers of bands may be used. The bands may be between first and second upper and lower frequency limits, for example, between 200 and 6300 Hz, although it is understood that other limits may be used.

[0057] The Al can be calculated as follows: AI=∑i=1nWi[(SNRi+n)30] where W i a weighting given to each frequency band, which indicates the importance of that band on speech recognition, SNR i is a speech-to-noise ratio in band i, which is determined as the difference between the root mean square (rms) of the speech level and the rms of the noise level, and n is a predetermined value to represent a speech level peak, which may be a value of 12. It is noted that W i does not have to be the same for all bands and that a different W i-value can be used for each band. In particular, so that the determined AI reflects the intelligibility of the speech of the occupant of the second zone 150, the weighting of frequency bands corresponding to those of the occupant's voice can be increased by the SIM 310 as a function of the signal from the second audio input means 170 of the second zone 150 such that frequency bands that have a larger signal due to speech in the second zone 150 have an increased weighting.

[0058] It can be seen that the bracketed quantity in the above equation has a value from 0 to 1, and if 20 bands are used, each band can have a weight of 0.05, so that the Al is determined as a value between 0 and 1, although it can be seen that other numbers of bands and weights can be used, which can lead to different upper and lower limits.

[0059] In other embodiments, as mentioned above, the SIM 310 may receive data indicative of one or more characteristics of the vehicle 100 from the vehicle system 260. For example, the SIM 310 may receive speed data or drive motor speed data via the communication bus 210. Based on predetermined characteristics of the vehicle 100, in some embodiments the SIM 310 may estimate speech intelligibility depending on the data indicative of one or more characteristics of the vehicle 100. For example, it may be determined that AI decreases within an increasing vehicle speed and / or drive motor speed.

[0060] The SIM 310 is arranged to compare the determined AI with a predetermined AI threshold. If the AI is above the threshold, it is determined that the speech is intelligible to the occupant of the first zone 110. The threshold may be a value of 0.3, although it is understood that this is only an example and that other thresholds may be used.

[0061] If the determined AI is above the AI threshold, a signal may be provided to the MM 320 to output audio to the first zone 110 to mask the speech, thereby reducing the AI of the first zone 110. The audio is output from the audio output means 146, 147 associated with the first zone 110. The audio is provided to the MM 320 from the audio source means 250 as the audio signal 205. The audio signal 205 may, in some embodiments, be representative of Brownian, white, or pink noise. In other embodiments, the audio source means is a music source, a radio, or a streaming audio source.

[0062] The output audio has one or more features controlled by the MM 320 to mask speech. In some embodiments, the one or more features include a frequency profile of the audio signal. The MM 320 may include a filter or a series of filters, each having a predetermined bandpass, so that the frequency profile of the audio can be controlled by the MM 320. The MM 320 may control the filters to increase the volume of the audio output in the first zone 110 in one or more frequency bands relative to the volume of the audio output in other frequency bands to mask speech in the second zone 150.

[0063] In some embodiments, the controller 200 executes a speech determination module (SDM) 330 and / or a head position module (HPM) 340, or both.

[0064] The SDM 330 is arranged to determine one or more speech characteristics of an occupant in the vehicle 100. In particular, in the exemplary embodiment, the SDM 330 is arranged to determine one or more frequency bands in which the occupant of the second zone 150 speaks. For example, if the occupant of the second zone is a young woman, her speech is expected to occupy one or more relatively higher frequency bands than, for example, an older man. In one embodiment, the SDM 330 may access data indicating occupant characteristics such as gender and age. However, in other embodiments, the SDM 330 receives the signal from the audio input means 170 of the second zone 150 to determine the frequency characteristics of the occupant's voice of the second zone based thereon. The SDM 330 may provide data that sends frequency band weights to one or both of the SIM 310 and the MM 320. The SIM 310 may determine the value of W ifor each frequency band based thereon. The MM 320 may control the frequency characteristics of the audio output in the first zone 110, for example, by varying the plurality of filters acting on the audio signal 205 to determine the audio output in the frequency bands corresponding to speech in the second zone 150 relative to the volume of the audio output in other frequency bands. In this way, the audio output in the first zone 110 from the MM 320 is targeted to frequency bands corresponding to the speech of the occupant in the second zone 150.

[0065] In some embodiments, the HPM 340 is arranged to receive the image data from the head position determining means 135, which, as mentioned above, may be one or more cameras or imaging devices arranged in the vehicle 100. The HPM 340 is arranged to operatively determine the position of a head of at least one occupant of the vehicle. In the example of Fig. 1, the HPM 340 is arranged to receive image data corresponding to an image of the occupant of the first zone. The HPM 340 is arranged to determine the position of the occupant's head from the received image data. In particular, in some embodiments, the HPM 340 is arranged to determine the position of the occupant's head relative to the plurality of audio output means 146, 147 having the occupant's zone, for example, the first zone 110, as in the example. The HPM 340 determines the position of the occupant's head relative to each of the plurality of audio output devices 146, 147. For example, if a first and a second audio output device 146, 147 are disposed in each side of the headrest of the seat in the first zone 110, the HPM 340 determines whether the head is tilted toward one side or the other, thus determining a relative proximity to each of the audio output devices 146, 147.The position-indicating data is provided from the HPM 340 to the MM 320. In some embodiments, the MM 320 controls a volume of the audio signal provided to each audio output device 146, 147 to equalize the audio amplitude at each ear of the occupant. In this way, the occupant of the first zone 110 is provided with relatively equal masking audio even when the head is tilted. It should be understood that the HMP 340 and the MM 320 may control the volumes of audio provided to other audio output devices within the first zone, in addition to or alternatively to the headrest-mounted audio output devices.

[0066] Fig.4 shows a method 400 according to one embodiment of the invention. The method 400 is a method for masking speech in a vehicle according to one embodiment of the invention. The method 400 can be executed by a processing device such as the control device 200 described above.

[0067] The method 400 includes a step 410 for determining whether a trigger event has occurred. The trigger may be the receipt of a user input indicating a request for the method 400 to be performed. The user input may be provided by an occupant of the vehicle, such as, but not limited to, the occupant of the second zone 150. The input indicates a desire for speech to be masked within the vehicle 100. The user input may be provided to a switching device within the vehicle 100 or to a graphical user interface (GUI), for example, via a user-selectable control of the GUI. In other embodiments, the trigger may be a telephone call received at the vehicle 100, for example, via a hands-free system of the vehicle. If no trigger is received, the method waits in step 410, i.e.it repeats until a trigger is received, when the method continues to step 420.

[0068] In step 420, method 400 determines an estimate of speech intelligibility. The estimate may be determined as described above with respect to SIM 310. Specifically, the estimate may be determined as the Al of speech in one zone of the interior of vehicle 100, for example, first zone 110. The speech may originate from an occupant of another zone of the vehicle, for example, second zone 150.

[0069] In step 430, it is determined whether the speech is intelligible. The determination in step 430 is made with reference to the estimate determined in step 420. In particular, the speech intelligibility estimate determined in step 420 is compared to an intelligibility threshold. In one embodiment, the value of Al determined in step 420 is compared to an Al threshold in step 430. The Al threshold may be, for example, 0.3. If the determined Al exceeds the Al threshold, the speech is determined to be intelligible and the method proceeds to step 440. If it is determined that the speech is not intelligible, e.g., if the determined Al is below the threshold, the method returns to step 420 where the Al is redetermined. A delay may be included before the Al is redetermined.For example, the delay can be a value of 10 seconds, 30 seconds, or 1 minute, although other delay values can be used.

[0070] In step 440, one or more characteristics of an audio signal are determined for masking speech. In some embodiments, the one or more characteristics include a frequency distribution of the audio signal. The frequency distribution may be controlled such that the audio signal includes a larger signal, i.e., is louder, in one or more frequency bands. The frequency bands in which the signal is controlled to have a larger amplitude may include those bands corresponding to the occupant's voice.

[0071] In step 450, the audio signal is output. The audio signal is delivered to one or more audio output means 146, 147.

[0072] It should be noted that embodiments of the invention may be embodied in the form of hardware, software, or a combination of hardware and software. Such software may be stored in the form of volatile or non-volatile storage, such as a storage device such as ROM, whether erasable or rewritable or not, or in the form of memories such as RAM, memory chips, devices, or integrated circuits, or on an optically or magnetically readable medium such as a CD, DVD, magnetic disk, or magnetic tape. It should be noted that the storage devices and storage media are embodiments of machine-readable memories suitable for storing a program or programs that, when executed, implement embodiments of the invention.Accordingly, embodiments provide a program comprising code for implementing a system or method as claimed in any preceding claim, and a machine-readable memory storing such a program. Furthermore, embodiments of the invention may be communicated electronically via any medium, such as a communication signal transmitted over a wired or wireless connection, and embodiments accordingly include the same.

[0073] All features disclosed in this specification (including any accompanying claims, the abstract, and the drawings) and / or all steps of any method or process so disclosed may be combined in any combination, except for combinations in which at least some of these features and / or steps are mutually exclusive.

[0074] Any feature disclosed in this specification (including any accompanying claims, the abstract, and drawings) may be replaced by alternative features that achieve the same, corresponding, or similar purposes, unless expressly stated otherwise. Therefore, unless otherwise stated, each disclosed feature is merely an example of a generic set of equivalent or similar features.

[0075] The invention is not limited to the details of any of the above embodiments. The invention extends to any single novel feature or any novel combination of features disclosed in this specification (including any accompanying claims, the abstract, and the drawings) or any single novel feature or any novel combination of steps of any method or process so disclosed. The claims should not be construed to cover only the above embodiments, but also to cover any embodiments falling within the scope of the claims.

Claims

[1] In-vehicle privacy system comprising: Audio output means (146, 147) associated with a first zone (110) of a vehicle (100); Audio source means (250) for sending an audio signal (205) to the audio output means (146, 147); Speech intelligibility means (310) for estimating speech intelligibility in the first zone (110); Control means (200) arranged to control one or more properties of the audio signal (205) in dependence on the speech intelligibility estimate in order to mask the speech of a second occupant in a second zone (150) of the interior of the vehicle from a first occupant in the first zone (110); wherein the speech intelligibility means (310) is arranged to receive data on one or more parameters of the vehicle and to estimate the speech intelligibility in dependence thereon; wherein the one or more parameters comprise one or more of vehicle speed, drive motor speed, and engine speed. [2] The system of claim 1, wherein the one or more properties of the audio signal (205) comprise a frequency profile of the audio signal (205). [3] The system of claim 1 or 2, wherein the audio source means (250) comprises a noise source. [4] The system of claim 3, wherein the noise source is a Brownian, white, or pink noise source. [5] A system according to any preceding claim, wherein the audio source means (250) comprises an audio source; optionally, the audio is provided by a music source, a radio source, or a streaming source. [6] A system according to any one of the preceding claims, wherein the speech intelligibility means (310) is arranged to receive a signal from an audio input means (130) arranged in the first zone (110) and to estimate the speech intelligibility in dependence thereon. [7] A system according to any one of the preceding claims, wherein the estimate of speech intelligibility is an articulation index (AI). [8] System according to one of the preceding claims, comprising: a plurality of audio output means (146, 147) associated with a first zone (110); Head position determining means (135) for determining a head position of the first occupant and outputting data indicative of the head position; wherein the control means (200) is arranged to send the audio signal (205) to the plurality of audio output means (146, 147) in dependence thereon. [9] A system according to any one of the preceding claims, wherein the audio output means (146, 147) associated with the first zone (110) comprises one or more audio output devices arranged in the first zone (110) of the interior of the vehicle. [10] The system of claim 9, wherein the one or more audio output devices are disposed in a headrest of a seat in the first zone (110). [11] A system according to any preceding claim, wherein the control means is arranged to control the one or more properties of the audio signal (205) to reduce the estimate of speech intelligibility. [12] A method for masking speech in a vehicle, comprising Estimating speech intelligibility in a first zone (110) of an interior of a vehicle; Controlling one or more properties of an audio signal (205) in dependence on the speech intelligibility estimate; and Outputting the audio signal (205) in the first zone (110) to mask the speech of a second occupant in a second zone (150) of the interior of the vehicle from a first occupant in the first zone (110); wherein estimating speech intelligibility comprises receiving data on one or more parameters of the vehicle and estimating speech intelligibility in dependence thereon; wherein the one or more parameters comprise one or more of vehicle speed, drive motor speed, and engine speed. [13] The method of claim 12, wherein estimating speech intelligibility comprises receiving an audio signal from the first zone (110) of the interior of the vehicle and estimating speech intelligibility in dependence thereon. [14] A method according to claim 12 or 13, wherein the estimate of speech intelligibility is an articulation index (AI). [15] The method of any one of claims 12 to 14, wherein the one or more properties of the audio signal (205) are controlled to reduce the estimate of speech intelligibility. [16] The method of any one of claims 12 to 15, wherein controlling one or more properties of the audio signal (205) comprises controlling a frequency distribution of the audio signal. [17] The method of any one of claims 12 to 16, wherein the audio signal (205) comprises a representation of a noise signal; optionally, the noise signal is Brownian, white, or pink noise. [18] The method of any one of claims 12 to 17, wherein the audio signal (205) is output to mask speech of a second occupant in a second zone (150) of the interior of the vehicle from a driver of the vehicle. [19] Computer software which, when executed on a computer, is adapted to carry out a method according to any one of claims 12 to 18; optionally the computer software is stored on a computer-readable data carrier. [20] A vehicle comprising an in-vehicle privacy system according to any one of claims 1 to 11, or comprising the computer software of claim 19.

Images