{"segments": [[13.0, 14.67], [17.0, 22.0], [22.0, 27.0], [32.0, 37.0], [63.0, 64.49], [76.0, 77.25]], "p_music": [0.0, 0.0, 20.12, 18.48, 0.0, 0.0], "p_speech": [0.0, 17.54, 39.25, 32.76, 0.0, 21.82], "labels": ["P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 17.54", "P(~Music) = 20.12 | P(~Speech) = 39.25", "P(~Music) = 18.48 | P(~Speech) = 32.76", "P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 21.82"]}