{"segments": [[23.0, 28.0], [28.0, 33.0], [43.0, 48.0], [48.0, 53.0], [53.0, 58.0]], "p_music": [0.0, 0.0, 0.0, 7.31, 22.56], "p_speech": [0.0, 18.17, 0.0, 34.11, 0.0], "labels": ["P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 18.17", "P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 7.31 | P(~Speech) = 34.11", "P(~Music) = 22.56 | P(~Speech) = 0.0"]}