Search

EP-4163911-B1 - A SYSTEM, A METHOD AND A COMPUTER PROGRAM PRODUCT FOR SILENCING A PERSON

EP4163911B1EP 4163911 B1EP4163911 B1EP 4163911B1EP-4163911-B1

Inventors

  • GARDTMAN, Angelika
  • NILSSON, MAGNUS

Dates

Publication Date
20260506
Application Date
20211006

Claims (12)

  1. A vehicle comprising a system (100) for silencing a person, the vehicle system (100) comprises: a microphone (10a,10b,10c,10d) configured to obtain sound of a first person (1), wherein the first person (1) is a vehicle occupant; a speaker (20a,20b,20c,20d) configured to playback sound to the first person (1), wherein the speaker and/or microphone are installed in the vehicle; a processing circuitry (102a,102b,102c) connected to the microphone (10a,10b,10c,10d) and the speaker (20a,20b,20c,20d) and configured to: - obtain sound of the first person (1) by the microphone (10a,10b,10c,10d); and characterized in that the processing circuitry (102a, 102b, 102c) is further configured to: - determine if the obtained sound of the first person (1) is above a predefined sound level; and - if the sound of the first person (1) is above the predefined sound level, play back the obtained sound of the first person (1) with a predefined time delay (td) by the speaker (20a,20b,20c,20d).
  2. The vehicle according to claim 1, wherein the predefined sound level is set dynamically based on the sound level of an ambient sound.
  3. The vehicle according to any preceding claims, wherein the processing circuitry (102a,102b,102c) is further configured to: - determine if the duration of the sound of the first person (1) exceeds a predefined time.
  4. The vehicle according to any of the preceding claims, wherein the system (100) further comprises: a camera (30a,30b) configured to obtain an image of a second person (2); and the processing circuitry (102a,102b,102c) is connected to the microphone (10a,10b,10c,10d), the speaker (20a,20b,20c,20d) and the camera (30a,30b) and further configured to: - obtain an image of a facial expression of a second person (2) by the camera (30a,30b); and - determine if the obtained facial expression of the second person (2) corresponds to a predetermined facial expression associated with a first facial expression category.
  5. The vehicle according to claim 4, wherein the processing circuitry (102a,102b,102c) is further configured to: - determine if the obtained facial expression of the second person (2) is obtained while sound of the first person (1) is obtained.
  6. The vehicle according to any of the preceding claims, wherein the processing circuitry (102a,102b,102c) is further configured to: - obtain sound of a second person (2) by the microphone (10a,10b,10c,10d); and - determine by sound recognition if the obtained sound of the second person (2) corresponds to a predetermined sound associated with a first sound category.
  7. The vehicle according to any of the preceding claims, wherein the processing circuitry (102a,102b,102c) is further configured to: - determine a total time when sound is obtained from the first person (1); and - determine when the total time of sound from the first person (1) exceeds a predefined time period.
  8. A method for silencing a person in the vehicle of any of the above claims comprising: - (S1) obtaining sound of a first person (1) by the microphone (10a,10b,10c,10d), wherein the first person (1) is a vehicle occupant; characterized by : - (S2) determining if the obtained sound of the first person (1) is above a predefined sound level by the processing circuitry (102a,102b,102c) connected to the microphone (10a,10b,10c,10d) and a speaker (20a,20b,20c,20d); and - (S9) if the sound of the first person (1) is above the predefined sound level, playing back the obtained sound of the first person (1) with a predefined time delay (td) by the speaker (20a,20b,20c,20d).
  9. The method according to claim 8 further comprising: - (S3) determining if the duration of the sound of the first person (1) exceeds a predefined time.
  10. The method according to any of the claims 8-9 further comprising: - (S4) obtaining an image of a facial expression of a second person (2) by a camera (30a,30b); and - (S5) determining if the obtained facial expression of the second person (2) corresponds to a predetermined facial expression associated with a first facial expression category.
  11. The method according to claim 10 further comprising: - (S6) determining if the obtained facial expression of the second person (2) is obtained while sound of the first person (1) is obtained.
  12. The method according to any of the claims 8-11 further comprising: - (S7) obtaining sound of a second person (2) by the microphone (10a,10b,10c,10d); and - (S8) determining by sound recognition if the obtained sound of the second person (2) corresponds to a predetermined sound associated with a first sound category

Description

Technical field The present disclosure relates to a system, a method and a computer program product for discreetly silencing a person in a polite way, such as silencing a vehicle occupant in a vehicle to not disturb other vehicle occupants in the vehicle. Background art Talking, singing or whistling etc. may not always be socially accepted. There are occasions when persons are close to each other and it is expected and desired that every person is silent to not disturb others. In an example, when travelling together in a shared vehicle you sometimes want the other persons to be silent. One reason is that you are sitting close to each other and it is therefore very easy to annoy each other by making sound, e.g. talking in a phone etc. There are also vehicles and sections in vehicles that have silent compartments. A person that has e.g. pre-booked to travel in a silent compartment, expects it to be silent. However, there are unfortunately not all that respect to be silent and this can sometimes be disturbing to others. Today you could ask a person to be quiet. There are also solutions to cancel noise and speech by active noise canceling headphones etc. However, this is not always a very practical solution. Kyle.Engineers: "Speech Jammer Car Review", 6 June 2013, URL:https://www.youtube.com/watch? v=B5pMqP_uDzl&ab_channel=KYLE.ENGINEERS discloses a method/system for silencing a vehicle occupant based on delayed auditory feedback. Summary It is an object of the present disclosure to mitigate, alleviate or eliminate one or more of the above-identified deficiencies and disadvantages in the prior art and solve at least the above mentioned problem. According to a first aspect there is provided a vehicle system for silencing a person. The vehicle system comprises a microphone configured to obtain sound of a first person, wherein the first person is a vehicle occupant, a speaker configured to playback sound to the first person, a processing circuitry connected to the microphone and the speaker and configured to obtain sound of the first person by the microphone, and determine if the obtained sound of the first person is above a predefined sound level, and if the sound of the first person is above the predefined sound level, play back the obtained sound of the first person with a predefined time delay by the speaker. One advantage with this first aspect is that when the first person hears his/her own voice played back with a small delay, like an echo, he/she will immediately cease talking since it is annoying. This is a discreet way of silencing the first person in a polite way without the need of someone else to ask the first person to be quiet. Another advantage with this first aspect is that sound below a certain predefined sound level can be allowed, e.g. whispering or talking with a low voice. According to some embodiments, the predefined sound level is set dynamically based on the sound level of an ambient sound. One advantage with this embodiment is that depending on the ambient sound, the predefined sound level is adjusted in order to adapt to allow a certain level of sound of the first person relatively to the ambient sound. According to some embodiments, the processing circuitry is further configured to determine if the duration of the sound of the first person exceeds a predefined time. One advantage with this embodiment is that the first person may be allowed to make sound during a predefined time that may not be considered as disturbing e.g. polite short phrases, or shortly answering the phone etc. According to some embodiments, the system further comprises a camera configured to obtain an image of a second person, and the processing circuitry is connected to the microphone, the speaker and the camera and further configured to obtain an image of a facial expression of a second person by the camera and determine if the obtained facial expression of the second person corresponds to a predetermined facial expression associated with a first facial expression category. One advantage with this embodiment is that it can be determined if the second person is making a facial expression that belongs to a first facial expression category such as a disapproving facial expression. According to some embodiments, the processing circuitry is further configured to determine if the obtained facial expression of the second person is obtained while sound of the first person is obtained. One advantage with this embodiment is that it can be determined if the obtained facial expression of the second person occurs while the first person is making a sound to e.g. determine if the sound the first person is making is approved or disapproved by the second person. According to some embodiments, the processing circuitry is further configured to obtain sound of a second person by the microphone, and determine by sound recognition if the obtained sound of the second person corresponds to a predetermined sound associated with a first sou