This refeerence to the poem is featured at the beginning of the second stanza, where the speaker comments on the difference between the kind of music that is a product of his own world and the kind of music that is a product of the world of the urn, which is the world of eternal beauty:
Heard melodies are sweet, but those unheard
Are sweeter; therefore, ye soft pipes, play on;
Not to the sensual ear, but, more endeared,
Pipe to the spirit dities of no tone.
The speaker is describing what he sees on the urn. The contrast between the "Heard melodies" and the "unheard" melodies links to the contrast that is established throughout the poem: the difference between the ephemeral and marred nature of human existence and the perfect state of art. The "unheard" melodies of art are actually purer and perfect precisely because we cannot hear them and therefore do not involve our hearing to perceive them. The "spirit" that they appeal to is able to give them therefore a beauty and perfection that is unattainable to songs that are heard by the "sensual ear." This description therefore refers to the difference between the world of the speaker and the world of beauty.