Music semantic annotation aims to automatically annotate a music signal with a set of semantic labels using words or tags. Usually, multilabel learning is done by transforming into multiple independent binary classification problems and model each semantic label individually. In order to produce better classification result, label correlations should be taken into account. In this paper, we try to use collective music semantic annotation, which not only builds a model for each semantic label, but also builds models for the pairs of labels that have significant correlations. We use multilabel conditional random fields(CRF) model to parametric the cooccurrence of multilabel classification. Two CRF models are proposed here, one is called collective multilabel classifier(CML) while utilized unconditional label correlation; while the other is called collective multilabel with features classifier(CMLF) which utilizes conditional label correlation. Experiments show that using these two models have higher average accurancy, macroaveraged F1 score and microaveraged F1 score than using Guassian mixture model on the issue of semantic annotation while using CAL10K datasets.