With the development of music information retrieval, melody extraction has become an important research direction. The research results of this task show great application potential in many fields, such as music transcription, cover song recognition and humming query system. In this paper, a melody extraction algorithm based on dual-branch fusion and spatial directional attention is proposed. The traditional feature representation method needs to suppress the harmonic and sub-harmonic signals, which will bring some information loss in the process of preprocessing. In order to improve the effectiveness of the input feature representation, a pre-trained network model for extracting high-level semantic features in audio is introduced to form a dual-branch structure with the original feature input. On this basis, a feature fusion module is proposed to mine the deep-level feature information and realize multi-granularity feature integration. Meanwhile, in order to improve the feature extraction efficiency, the channel convolution module is proposed in this paper, and a new attention mechanism is proposed to efficiently acquire fine-grained local feature information from both horizontal and vertical directions. Our proposed melody extraction algorithm, which leverages dual-branch fusion and spatial-directional attention, exceeds existing methods by 0.9% to 2.61% across three datasets, demonstrating the model’s effectiveness and robust generalization capability across diverse data sources.