Text-embedding clustering for batch sampling outperforms audio-embedding clustering on objective metrics in low-data text-to-music generation, with moderate cluster counts best on metrics and larger counts better for structural coherence in listening tests.
Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML 2019) , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
UT-AISTimprt submission for ICME 2026 Grand Challenge on Academic Text-to-Music Generation
Text-embedding clustering for batch sampling outperforms audio-embedding clustering on objective metrics in low-data text-to-music generation, with moderate cluster counts best on metrics and larger counts better for structural coherence in listening tests.