KR-102961727-B1 - SOUND QUALITY IMPROVEMENT BASED ON ARTIFICIAL INTELLIGENCE

Abstract

Artificial intelligence-based sound quality improvement is initiated. An artificial intelligence-based sound control method according to one embodiment of the present specification provides different call quality for each person based on a plurality of person information stored in the address book of a mobile terminal. The mobile terminal and 5G network of the present specification may be linked with an artificial intelligence module, a drone (Unmanned Aerial Vehicle, UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to 5G services, etc.

Inventors

• 오상준
• 황승현
• 김영만
• 이규호
• 정재웅

Assignees

• 엘지전자 주식회사

Dates

Publication Date

20260508

Application Date

20200330

Claims (20)

1. Through the processor, A step of generating one or more sets of person information including one or more person information based on the attributes of a sound signal; A step of performing a task to adjust the parameters of an audio equalizer based on information representing the above-mentioned person information set and the feature vector of the above-mentioned sound signal using a machine learning model; Includes, The parameters of the above audio equalizer are mapped to the above person information and stored in memory, and When receiving a user's call signal corresponding to the person information stored in the above memory, Through the above processor, A step of loading parameters of an audio equalizer stored in the memory in response to the above call signal; and A step of controlling the call quality output through the speaker based on the parameters of the loaded audio equalizer; An artificial intelligence-based acoustic control method that further includes
2. In paragraph 1, Through the above processor, A step of receiving the sound signal through a transmitting and receiving unit while performing a wireless call with a mobile terminal connected via a network; and A step of storing the received sound signal in memory; Including more, An artificial intelligence-based sound control method characterized in that the above sound signal includes a voice signal obtained through the microphone of the mobile terminal connected to the communication.
3. In paragraph 1, An artificial intelligence-based acoustic control method characterized by the above attributes including a volume for each of a plurality of frequency bands.
4. ◈Claim 4 was waived upon payment of the establishment registration fee.◈ In paragraph 3, The step of generating the above person information set is, A step of calculating similarity by comparing the attributes of two or more individuals by frequency band; A step of distinguishing two or more person information based on the above similarity; and A step of generating the person information set including the above-described two or more person information sets; An artificial intelligence-based acoustic control method characterized by including
5. ◈Claim 5 was waived upon payment of the establishment registration fee.◈ In paragraph 3, The above plurality of frequency bands includes the first to Nth bands (N is a natural number), and An artificial intelligence-based acoustic control method characterized in that the frequency bandwidth of the K-th band (K is a natural number greater than or equal to 2, K < N) is an integer multiple of the frequency bandwidth of the K-1th band.
6. ◈Claim 6 was waived upon payment of the establishment registration fee.◈ In paragraph 1, When the parameters of the above audio equalizer change from a first state to a second state distinct from the first state, Through the above processor, An artificial intelligence-based acoustic control method characterized by performing reinforcement learning to adjust the parameters of the machine learning model based on the difference between the first and second states.
7. In paragraph 1, An artificial intelligence-based acoustic control method characterized by adjusting the parameters of the machine learning model in response to receiving feedback on the result of performing the task through the above processor.
8. ◈Claim 8 was waived upon payment of the establishment registration fee.◈ In Paragraph 7, An artificial intelligence-based sound control method characterized in that the above feedback is an input that adjusts the parameters of an audio equalizer through a user interface.
9. delete
10. delete
11. Transmitter/receiver receiving sound signals through a network; A memory in which one or more person information is recorded; and A processor that generates one or more sets of person information including one or more person information based on the attributes of the sound signal, and performs a task of adjusting parameters of an audio equalizer based on information representing the sets of person information and a feature vector of the sound signal using a machine learning model; Includes, The parameters of the above audio equalizer are mapped to the above person information and stored in the above memory, and The above processor is, An intelligent mobile terminal that, upon receiving a user call signal corresponding to person information stored in the memory, loads parameters of an audio equalizer stored in the memory in response to the call signal, and controls the call quality output through a speaker based on the loaded parameters of the audio equalizer.
12. In Paragraph 11, The above processor is, Control the transceiver to receive the sound signal while performing a wireless call with another mobile terminal connected via the above network, and store the received sound signal in memory. An intelligent mobile terminal characterized in that the above sound signal includes a voice signal obtained through the microphone of the other mobile terminal.
13. In Paragraph 11, An intelligent mobile terminal characterized by the above attributes including a volume for each of a plurality of frequency bands.
14. ◈Claim 14 was waived upon payment of the establishment registration fee.◈ In Paragraph 13, The above processor is, An intelligent mobile terminal characterized by calculating similarity by comparing the attributes of two or more people by frequency band, distinguishing the information of the two or more people based on the similarity, and generating the set of information of people including the distinguished information of the two or more people.
15. In Paragraph 11, The above processor is, An intelligent mobile terminal characterized by performing reinforcement learning to adjust the parameters of a machine learning model based on the difference between the first and second states when the parameters of the audio equalizer change from a first state to a second state distinct from the first state.
16. In Paragraph 11, The above processor is, An intelligent mobile terminal characterized by adjusting the parameters of the machine learning model in response to receiving feedback on the result of performing the above task.
17. ◈Claim 17 was waived upon payment of the establishment registration fee.◈ In Paragraph 16, An intelligent mobile terminal characterized in that the above feedback is an input that adjusts the parameters of an audio equalizer through a user interface.
18. delete
19. delete
20. A computer system-readable recording medium having a program recorded thereon for executing the method of any one of paragraphs 1 through 8 on a computer system.

Description

Sound Quality Improvement Based on Artificial Intelligence This specification relates to artificial intelligence-based sound quality improvement. Artificial intelligence technology consists of machine learning (deep learning) and elemental technologies utilizing machine learning. Machine learning is an algorithmic technology that classifies and learns the features of input data on its own, and the elemental technology is a technology that mimics the functions of the human brain, such as cognition and judgment, by utilizing machine learning algorithms such as deep learning, and consists of technology fields such as linguistic understanding, visual understanding, reasoning/prediction, knowledge representation, and motion control. Meanwhile, artificial intelligence technology can also be applied to call services via mobile terminals. In conventional call services, there is a limitation in that the call quality of mobile terminals is not personalized according to the sound features of the user or the far-end, and is output at a constant level. Technologies related to AI-based call quality improvement are disclosed in Korean Published Patent Application No. 10-2019-0106916 (September 18, 2019) and Korean Published Patent Application No. 10-2011-0016036 (February 17, 2011). The accompanying drawings, included as part of the detailed description to aid in understanding the present specification, provide embodiments of the present specification and explain the technical features of the present specification together with the detailed description. FIG. 1 illustrates a block diagram of a wireless communication system to which the methods proposed in this specification can be applied. Figure 2 shows an example of a signal transmission/reception method in a wireless communication system. Figure 3 shows an example of the basic operation of a user terminal and a 5G network in a 5G communication system. FIG. 4 is a block diagram of an AI device according to one embodiment of the present specification. FIG. 5 is a block diagram for explaining a mobile terminal related to the present specification, and FIG. 6 and FIG. 7 are conceptual diagrams of an example of a mobile terminal related to the present specification viewed from different directions. FIG. 8 is a conceptual diagram showing one embodiment of an AI device. FIG. 9 is a flowchart of an artificial intelligence-based acoustic control method according to one embodiment of the present specification. FIG. 10 is a flowchart for specifically explaining S120 of FIG. 9. Figure 11 is a flowchart of a reinforcement learning algorithm for a machine learning model. Figure 12 is a flowchart of an acoustic control method based on a learned machine learning model. Figure 13 is a sequence diagram of an acoustic control method based on a 5G network. FIGS. 14 and FIGS. 15 are drawings for explaining an embodiment of an acoustic control method according to one embodiment of the present specification. Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components regardless of drawing symbols will be assigned the same reference number, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not inherently possess distinct meanings or roles. Furthermore, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art could obscure the essence of the embodiments disclosed in this specification, such detailed description will be omitted. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification; the technical concept disclosed in this specification is not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the concept and technical scope of this specification. Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. A singular expression includes a plural expression unless the context clearly indicates otherwise. In this application, terms such as “comprising” or “having” are inte