{"segments": [[29.0, 34.0], [90.0, 92.62], [110.0, 115.0], [127.0, 132.0]], "p_music": [11.93, 14.71, 0.0, 6.21], "p_speech": [44.22, 38.86, 43.06, 49.39], "labels": ["P(~Music) = 11.93 | P(~Speech) = 44.22", "P(~Music) = 14.71 | P(~Speech) = 38.86", "P(~Music) = 0.0 | P(~Speech) = 43.06", "P(~Music) = 6.21 | P(~Speech) = 49.39"]}