CQTXNet: A Modified Xception Network with Attention Modules for Cover Song Identification
Jinsoo Seo, Jung-Hyun Kim, Hyemi Kim · IEICE Transactions on Information and Systems · 2023
Song-level feature summarization is fundamental for the browsing, retrieval, and indexing of digital music archives. This study proposes a deep neural network model, CQTXNet, for extracting song-level feature summary for cover song identification. CQTXNet incorporates depth-wise separable convolution, residual network connections, and attention models to extend previous approaches. An experimental evaluation of the proposed CQTXNet was performed on two publicly available cover song datasets by varying the number of network layers and the type of attention modules.