{"segments": [[17.0, 18.98], [22.0, 23.33], [27.0, 28.56], [32.0, 33.91], [39.0, 40.36], [42.0, 47.0], [47.0, 52.0], [52.0, 57.0], [88.0, 93.0]], "p_music": [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 16.33], "p_speech": [20.75, 0.0, 0.0, 12.04, 50.54, 0.0, 10.64, 0.0, 0.0], "labels": ["P(~Music) = 0.0 | P(~Speech) = 20.75", "P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 12.04", "P(~Music) = 0.0 | P(~Speech) = 50.54", "P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 10.64", "P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 16.33 | P(~Speech) = 0.0"]}