2022/10/02 by Kuang, Zhihuan, Zong, Shi, Zhang, Jianbing +2 · 1 citation
#Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Multimedia (cs.MM) #Sound (cs.SD) #electronic engineering #information engineering
paper · doi:10.48550/arxiv.2210.00434
In this paper, we consider a novel research problem: music-to-text synaesthesia. Different from the classical music tagging problem that classifies a music recording into pre-defined categories, music-to-text synaesthesia aims to generate descriptive texts from music recordings with the same sentiment for further understanding. As existing music-related datasets do not contain the semantic descriptions on music recordings, we collect a new dataset that contains 1,955 aligned pairs of classical music recordings and text descriptions. Based on this, we build a computational model to generate sentences that can describe the content of the music recording. To tackle the highly non-discriminative classical music, we design a group topology-preservation loss, which considers more samples as a group reference and preserves the relative topology among different samples. Extensive experimental results qualitatively and quantitatively demonstrate the effectiveness of our proposed model over five heuristics or pre-trained competitive methods and their variants on our collected dataset.