System and method of providing customized content by using sound

A method of providing customized content by using a sound, the method comprising:

• periodically collecting, by a recommendation server, waveform data of a sound with respect to content for each channel that is possibly output from one or more smart device which outputs the content for each channel received from a content provider;
• registering, by one or more user terminal after receiving a voice of a user with respect to a preset text for voice recognition, the voice of the user as voice data for user identification;
• receiving and transmitting, by the user terminal when a voice corresponding to the registered voice data for user identification is recognized while the smart device is in operation, waveform data of a sound of the content being output from the smart device and voice data of the user;
• and
• generating, by the recommendation server, interest information of the user when the waveform data and the voice data are transmitted from the user terminal
• wherein the recommendation server generates the interest information of the user based on the content that is output from the smart device, and
• wherein the content that is output from the smart device is specified by comparing the waveform data that is transmitted to the recommendation server from the user terminal and the waveform data that is periodically collected by the recommendation server.