Method, electronic device and recording medium for compensating in-ear audio signal

[0025]In the invention, objective functions are set for different applications of speech to establish a machine learning model, and the machine learning model is trained by using an in-ear audio signal transmitted through the inner ear of the user and an outer audio signal transmitted through air as parameters to obtain an audio signal feature between the in-ear audio signal and the outer audio signal. In an offline stage, the voice of the user is captured by an in-ear microphone, and a captured audio signal is input to the trained machine learning model for converting the captured audio signal into an output result close to the outer audio signal. Accordingly, the in-ear audio signal can be compensated to be close to an audio signal that is normally emitted by the user and transmitted through air.

[0026]FIG. 1 is a block diagram showing an electronic device according to an embodiment of the invention. Referring to FIG. 1, an electronic device 100 includes a processor 110, a connection