{"segments": [[22.0, 27.0], [27.0, 32.0]], "p_music": [0.0, 0.0], "p_speech": [59.88, 55.97], "labels": ["P(~Music) = 0.0 | P(~Speech) = 59.88", "P(~Music) = 0.0 | P(~Speech) = 55.97"]}