{"segments": [[29.0, 32.07], [52.0, 53.33], [56.0, 57.21], [61.0, 62.48]], "p_music": [0.0, 0.0, 5.2, 0.0], "p_speech": [0.0, 26.72, 18.18, 0.0], "labels": ["P(~Music) = 0.0 | P(~Speech) = 0.0", "P(~Music) = 0.0 | P(~Speech) = 26.72", "P(~Music) = 5.2 | P(~Speech) = 18.18", "P(~Music) = 0.0 | P(~Speech) = 0.0"]}