Intelligent audio processing

A method, comprising:

• in an electronic device:
• receiving, via a user interface, a first user input for a selection of a source audio signal,
• wherein the source audio signal is a composite audio signal including a plurality of audio signals;
• receiving, via the user interface, a second user input for a selection of a first operation of a plurality of operations to be performed on the source audio signal;
• receiving, via the user interface, a third user input for a selection of at least a first audio signal from the plurality of audio signals;
• applying a first machine learning (ML) model of a plurality of ML models on the source audio signal, based on the reception of the first user input and the third user input;
• extracting at least the first audio signal from the plurality of audio signals in the source audio signal based on the application of the first ML model on the source audio signal;
• applying, based on the reception of the second user input, a second ML model of the plurality of ML models on the extracted at least first audio signal to perform the selected first operation;
• generating output information related to the selected first operation, based on the application of the second ML model on the extracted at least first audio signal, wherein
• the first operation corresponds to an equalization of the source audio signal without an equalization of the extracted at least first audio signal,
• the generated output information indicates a final audio signal including equalized audio signals of the plurality of audio signals, and
• the equalized audio signals are different from the extracted at least first audio signal;
• and
• controlling an output device to render the generated output information.

A non-transitory computer-readable medium having stored thereon, computer-executable instructions that when executed by an electronic device, causes the electronic device to execute operations, the operations comprising:

• receiving, via a user interface, a first user input for a selection of a source audio signal,
• wherein the source audio signal is a composite audio signal including a plurality of audio signals;
• receiving, via the user interface, a second user input for a selection of a first operation of a plurality of operations to be performed on the source audio signal;
• receiving, via the user interface, a third user input for a selection of at least a first audio signal from the plurality of audio signals;
• applying a first machine learning (ML) model of a plurality of ML models on the source audio signal, based on the reception of the first user input and the third user input;
• extracting at least the first audio signal from the plurality of audio signals in the source audio signal based on the application of the first ML model on the source audio signal;
• applying, based on the reception of the second user input, a second ML model of the plurality of ML models on the extracted at least first audio signal to perform the selected first operation;
• generating output information related to the selected first operation, based on the application of the second ML model on the extracted at least first audio signal, wherein
• the first operation corresponds to an equalization of the source audio signal without an equalization of the extracted at least first audio signal,
• the generated output information indicates a final audio signal including equalized audio signals of the plurality of audio signals, and
• the equalized audio signals are different from the extracted at least first audio signal;
• and
• controlling an output device to render the generated output information.