[Retracted] Music Emotion Classification Method Based on Deep Learning and Explicit Sparse Attention Network

Table 4

Model classification accuracy under different data features.

Audio features	Happy	Sad	Relax	Anger	Average
LLDs	0.668	0.651	0.624	0.604	0.637
Spectrogram	0.657	0.643	0.665	0.623	0.647
LLDs + spectrogram	0.712	0.689	0.661	0.654	0.679