{"segments": [[16.0, 17.51], [50.0, 51.21], [114.0, 115.01]], "p_music": [0.0, 0.0, 11.73], "p_speech": [0.0, 7.22, 0.0], "labels": ["P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 7.22", "P(~Music) = 11.73 | P(~Speech) = 0.0"]}