A music-aware transformer framework combining multi-scale spectrogram learning and adaptive attention optimization reported ...
A computational study of GTZAN and ASAP audio datasets reports that the CCTAF-MSR CNN–Transformer model reached 86.40% precision, 88.99% recall and an 87.67% F1-score in GTZAN comparisons.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results