Granted Patent B2

US 12,548,541 · App. 18/385,695 · Granted Feb 10, 2026

Inventor: Kyoung Jin Chang (Gyeonggi-Do, KR)

Assignees: Hyundai Motor Company; Kia Corporation

G10K11/1754G01P15/00G06F3/165G10L25/18G10L25/30G10L25/51

Abstract

Claims (53)

1 . A sound system for a vehicle, the sound system comprising:

a noise meter configured to measure environmental noise generated around the vehicle;

a vibration meter configured to measure vibration generated by the vehicle; and

a processor connected with the noise meter and the vibration meter,

wherein the processor is configured to:

determine a noise type by analyzing features of the vibration and the environmental noise respectively measured by the vibration meter and the noise meter;

select a sound source matched with the noise type among sound sources previously stored in a database; and

play and output the selected sound source.

2 . The sound system of claim 1 , wherein the processor is configured to:

determine whether the vibration is greater than or equal to a predetermined reference level;

determine whether the vibration continues for at least a predetermined reference time in response to determining that the vibration is greater than or equal to the predetermined reference level; and

determine the noise type as road surface noise in response to determining that the vibration continues for at least the predetermined reference time.

3 . The sound system of claim 1 , wherein the processor is configured to:

analyze the environmental noise and extract a noise spectrum from the environmental noise; and

analyze the noise spectrum using an artificial intelligence (AI) model and classify the noise type.

4 . The sound system of claim 3 , wherein the processor is configured to perform short-time fast Fourier transform (FFT) of the environmental noise to calculate the noise spectrum.

5 . The sound system of claim 3 , wherein the noise spectrum is implemented as at least one of a Mel-spectrum or a constant-Q power spectrum.

6 . The sound system of claim 3 , wherein the AI model is composed of at least one of a convolutional neural network (CNN) algorithm or a long short-term memory (LSTM) algorithm.

7 . The sound system of claim 3 , wherein the processor is configured to classify a noise type of the environmental noise as any one of impact noise, continuity noise, conversational noise, or other noise.

8 . The sound system of claim 1 , wherein the processor is configured to:

analyze beat intensity, a volume change slope, a voice coverage rate, and other noise suitability for each of the previously stored sound sources;

store the analyzed results in the database; and

adjust a volume of the selected sound source based on levels of the vibration and the environmental noise.

9 . The sound system of claim 1 , wherein the noise meter includes a microphone configured to measure the environmental noise generated around the vehicle, and

wherein the vibration meter includes a vibration accelerometer configured to measure vibration acceleration using a vibration sensor installed in a delivery path in which road surface noise is delivered in the vehicle.

10 . A vehicle comprising the sound system of claim 1 .

11 . A method for implementing a sound of a sound system for a vehicle, the method comprising:

measuring environmental noise generated around the vehicle using a noise meter included in the sound system for the vehicle;

measuring vibration generated in the vehicle using a vibration meter included in the sound system for the vehicle;

determining, by a processor, a noise type by analyzing features of the vibration and the environmental noise;

selecting, by the processor, a sound source matched with the noise type among sound sources previously stored in a database included in the sound system for the vehicle; and

playing and outputting, by the processor, the selected sound source.

12 . The method of claim 11 , wherein the determining of the noise type includes:

determining whether the vibration is greater than or equal to a predetermined reference level;

determining whether the vibration continues for at least a predetermined reference time in response to determining that the vibration is greater than or equal to the predetermined reference level; and

determining the noise type as road surface noise in response to determining that the vibration continues for at least the predetermined reference time.

13 . The method of claim 11 , wherein the determining of the noise type includes:

analyzing the environmental noise and extracting a noise spectrum from the environmental noise; and

analyzing the noise spectrum using an AI model and classifying the noise type.

14 . The method of claim 13 , wherein the extracting of the noise spectrum includes:

performing short-time FFT of the environmental noise to calculate the noise spectrum.

15 . The method of claim 13 , wherein the noise spectrum is implemented as at least one of a Mel-spectrum or a constant-Q power spectrum.

16 . The method of claim 13 , wherein the AI model is composed of at least one of a convolutional neural network (CNN) algorithm or an LSTM algorithm.

17 . The method of claim 13 , wherein the extracting of the noise spectrum includes:

classifying a noise type of the environmental noise as any one of impact noise, continuity noise, conversational noise, or other noise.

18 . The method of claim 11 , further comprising:

analyzing beat intensity, a volume change slope, a voice coverage rate, and other noise suitability for each of the previously stored sound sources and storing the analyzed results in the database.

19 . The method of claim 11 , wherein the playing and outputting of the selected sound source includes:

adjusting volume of the selected sound source based on levels of the vibration and the environmental noise.

20 . The method of claim 11 , wherein the measuring of the environmental noise includes:

measuring the environmental noise generated around the vehicle using a microphone, and

wherein the measuring of the vibration includes:

measuring vibration acceleration using a vibration sensor installed in a delivery path in which road surface noise is delivered in the vehicle.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (19)