{"segments": [[25.0, 26.28], [66.0, 71.0]], "p_music": [12.5, 23.43], "p_speech": [6.91, 0.0], "labels": ["P(~Music) = 12.5 | P(~Speech) = 6.91", "P(~Music) = 23.43 | P(~Speech) = 0.0"]}