{"segments": [[6.0, 11.0], [11.0, 16.0], [52.0, 53.64], [63.0, 68.0], [74.0, 75.51]], "p_music": [0.0, 15.01, 24.76, 0.0, 0.0], "p_speech": [0.0, 0.0, 12.57, 13.02, 10.47], "labels": ["P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 15.01 | P(~Speech) = 0.0", "P(~Music) = 24.76 | P(~Speech) = 12.57", "P(~Music) = 0.0 | P(~Speech) = 13.02", "P(~Music) = 0.0 | P(~Speech) = 10.47"]}