Sound quality improvement based on artificial intelligence
AssigneeLG Electronics Inc.
InventorsSangjun Oh, Senghyun Huang, Youngman Kim, Kyuho Lee, Jaewoong Jeong
Life of this patent
Estimating the term…
Abstract
A sound quality improvement based on artificial intelligence is disclosed. A sound control method based on artificial intelligence according to an embodiment of the present disclosure provides a different call sound quality for each person based on a plurality of person information stored in an address book of a mobile terminal. The mobile terminal and 5G network of the present disclosure may be associated with an artificial intelligence module, a drone ((Unmanned Aerial Vehicle, UAV), a robot, an AR (Augmented Reality) device, a VR (Virtual Reality) device, a device associated with 5G services, etc.
Claims20
A sound control method based on artificial intelligence, comprising:
- obtaining a sound signal and mobile terminal information while performing a wireless call with a mobile terminal;
- generating at least one set of person information for a user of the mobile terminal comprising at least identification information for the mobile terminal and voice information based on an attribute of a sound signal, wherein the voice information is mapped to the at least one set of person information stored in a memory;
- and
- adjusting a parameter of an audio equalizer based on the generated at least one set of person information and a feature vector of the sound signal using a machine learning model, wherein the adjusted parameter of the audio equalizer is mapped to the generated at least one set of person information and stored in the memory.
An intelligent mobile terminal, comprising:
- a transceiver configured to obtain a sound signal and mobile terminal information while performing a wireless call with another mobile terminal connected to communicate through a network;
- a memory in which at least one person information is recorded;
- and
- a processor configured to:
- generate at least one set of person information for a user of the intelligent mobile terminal comprising at least identification information for the intelligent mobile terminal and voice information based on an attribute of the sound signal, wherein the voice information is mapped to the at least one set of person information stored in the memory;
- and
- adjust a parameter of an audio equalizer based on the generated at least one set of person information and a feature vector of the sound signal using a machine learning model, wherein the adjusted parameter of the audio equalizer is mapped to the generated at least one set of person information and stored in memory.
A non-statutory computer-readable recording medium on which a program for executing a method of:
- obtaining a sound signal and mobile terminal information while performing a wireless call with a mobile terminal;
- generating at least one set of person information for a user of the mobile terminal comprising at least identification information for the mobile terminal and voice information based on an attribute of a sound signal, wherein the voice information is mapped to the at least one set of person information stored in a memory;
- and
- adjusting a parameter of an audio equalizer based on the generated at least one set of person information and a feature vector of the sound signal using a machine learning model, wherein the adjusted parameter of the audio equalizer is mapped to the generated at least one set of person information and stored in the memory.
Dependencies are inferred from the claim text.