Automatic harmonic analysis of symbolic music is an important and useful task for both composers and listeners. The task consists of two components: recognizing harmony labels and finding their time boundaries. Most of the previous attempts focused on the first component, while time boundaries were rarely modeled explicitly. Lack of boundary modeling in the objective function could lead to segmentation errors. In this paper, we introduce a novel approach named Harana, to jointly detect the labels and boundaries of harmonic regions using neural semi-CRF (conditional random field). In contrast to rule-based scores used in traditional semi-CRF, a neural score function is proposed to incorporate features with more representational power. To improve the robustness of the model to imperfect harmony profiles, we design an additional score component to penalize the match between the candidate harmony label and the absent notes in the music. Quantitative results from our experiments demonstrate that the proposed approach improves segmentation quality as well as frame-level accuracy compared to previous methods.

If the video does not load properly please use the direct link to video