{"segments": [[3.0, 4.31], [26.0, 31.0], [35.0, 38.31], [61.0, 66.0], [76.0, 81.0], [100.0, 105.0], [105.0, 110.0]], "p_music": [0.0, 0.0, 14.27, 0.0, 0.0, 0.0, 12.41], "p_speech": [27.28, 51.8, 45.22, 40.55, 0.0, 37.15, 0.0], "labels": ["P(~Music) = 0.0 | P(~Speech) = 27.28", "P(~Music) = 0.0 | P(~Speech) = 51.8", "P(~Music) = 14.27 | P(~Speech) = 45.22", "P(~Music) = 0.0 | P(~Speech) = 40.55", "P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 37.15", "P(~Music) = 12.41 | P(~Speech) = 0.0"]}