Apparatus for generating driving sound in vehicle and method thereof
An apparatus for generating a driving sound in a vehicle includes a first conversion device that receives first sound information and converts the received first sound information into second sound information, a second conversion device that converts the second sound information into third sound information based on a conversion parameter, a storage that receives feedback information of a user about the third sound information and corrects and stores the third sound information, and a playback device that plays the stored third sound information.
1. An apparatus for generating a driving sound in a vehicle, the apparatus comprising:
a first conversion device configured to receive first sound information and convert the received first sound information into second sound information;
a second conversion device configured to convert the second sound information into third sound information based on a conversion parameter;
a storage configured to receive feedback information of a user about the third sound information and correct and store the third sound information; and
a playback device configured to play the stored third sound information according to driving of the vehicle,
wherein the first conversion device is configured to:
calculate sound pressure for each frequency, based on short-time Fourier transform with respect to one or more intervals included in the first sound information;
select an interval having a maximum sound pressure among the one or more intervals; and
convert the selected interval into the second sound information,
wherein the first sound information includes a sound selected by a user,
wherein the second sound information includes at least one interval to be converted into the driving sound of the vehicle, in the first sound information input by the user, and
wherein the third sound information indicates the driving sound of the vehicle, and the third sound information is configured to be corrected based on the feedback information to reflect personal preference of the user.
2. The apparatus of claim 1 ,
wherein the second sound information includes the at least one interval selected based on one of a first algorithm or a second algorithm among the one or more intervals included in the first sound information.
3. The apparatus of claim 2 , wherein the at least one interval selected based on the first algorithm includes an interval selected based on a convolutional neural network (CNN) algorithm among the one or more intervals, and
wherein the at least one interval selected based on the second algorithm includes an interval selected based on request information of the user among the one or more intervals.
4. The apparatus of claim 1 , wherein the conversion parameter includes a first parameter used to convert the second sound information into the third sound information and a second parameter about information used to play the third sound information.
5. The apparatus of claim 4 , wherein the first parameter includes at least one of a pitch conversion parameter or a gain conversion parameter, and
wherein the second parameter includes at least one of a power train (PT) rotation number parameter, a speed parameter, an acceleration parameter, or a torque parameter.
6. The apparatus of claim 1 , wherein the storage includes:
a classification device configured to classify the third sound information;
a feedback processing device configured to receive feedback information of the user about the classified third sound information and correct the classified third sound information based on the received feedback information of the user; and
a database configured to store the corrected third sound information.
7. The apparatus of claim 6 , wherein the classified third sound information indicates one of vehicle engine sound information, music sound information, alarm sound information, or voice information, and
wherein the database indicates one of a vehicle engine sound database, a music sound database, an alarm sound database, or a voice database.
8. The apparatus of claim 7 , wherein the classified third sound information is classified based on a CNN algorithm.
9. The apparatus of claim 6 , wherein the feedback information of the user indicates one of first feedback information indicative of correcting the classified third sound information or second feedback information indicative of not correcting the classified third sound information.
10. The apparatus of claim 9 , wherein the feedback information of the user is determined as the first feedback information or the second feedback information, based on at least one of heart rate information, blood flow information, body temperature information, pulse information, or brainwave information of the user.
11. A method for generating a driving sound in a vehicle, the method comprising:
receiving, by a first conversion device, first sound information and converting the received first sound information into second sound information;
converting, by a second conversion device, the second sound information into third sound information based on a conversion parameter;
receiving, by a storage, feedback information of a user about the third sound information and correcting and storing the third sound information; and
playing, by a playback device, the stored third sound information according to driving of the vehicle,
wherein converting the received first sound information into the second sound information includes:
calculating, by the first conversion device, sound pressure for each frequency, based on short-time Fourier transform with respect to one or more intervals included in the first sound information;
selecting, by the first conversion device, an interval having a maximum sound pressure among the one or more intervals; and
converting, by the first conversion device, the selected interval into the second sound information,
wherein the first sound information includes a sound selected by a user,
wherein the second sound information includes at least one interval to be converted into the driving sound of the vehicle, in the first sound information input by the user, and
wherein the third sound information indicates the driving sound of the vehicle, and the third sound information is configured to be corrected based on the feedback information to reflect personal preference of the user.
12. The method of claim 11 ,
wherein the second sound information includes the at least one interval selected based on one of a first algorithm or a second algorithm among the one or more intervals included in the first sound information.
13. The method of claim 12 , wherein the at least one interval selected based on the first algorithm includes an interval selected based on a CNN algorithm among the one or more intervals, and
wherein the at least one interval selected based on the second algorithm includes an interval selected based on request information of the user among the one or more intervals.
14. The method of claim 11 , wherein the conversion parameter includes a first parameter used to convert the second sound information into the third sound information and a second parameter about information used to play the third sound information.
15. The method of claim 14 , wherein the first parameter includes at least one of a pitch conversion parameter or a gain conversion parameter, and
wherein the second parameter includes at least one of a power train (PT) rotation number parameter, a speed parameter, an acceleration parameter, or a torque parameter.
16. The method of claim 11 , wherein the correcting and storing of the third sound information includes:
classifying the third sound information;
receiving feedback information of the user about the classified third sound information and correcting the classified third sound information based on the received feedback information of the user; and
storing the corrected third sound information in a database.
17. The method of claim 16 , wherein the classified third sound information indicates one of vehicle engine sound information, music sound information, alarm sound information, or voice information, and
wherein the database indicates one of a vehicle engine sound database, a music sound database, an alarm sound database, or a voice database.
18. The method of claim 17 , wherein the classified third sound information is classified based on a CNN algorithm.
19. The method of claim 16 , wherein the feedback information of the user is one of first feedback information indicative of correcting the classified third sound information or second feedback information indicative of not correcting the classified third sound information.
20. The method of claim 19 , wherein the feedback information of the user is determined as the first feedback information or the second feedback information, based on at least one of heart rate information, blood flow information, body temperature information, pulse information, or brainwave information of the user.