Topic
music generation
Artificial Intelligence #ai#music generation
UniSinger: First End-to-End Framework Unifies Song Generation and Singing Voice Conversion
Researchers have introduced UniSinger, the first end-to-end framework that unifies song generation and singing voice conversion with accompaniment co-generation. Built on a multimodal diffusion transformer, it enables zero-shot speaker cloning and fine-grained timbre control across tasks. Experiments demonstrate state-of-the-art performance on both tasks, offering new possibilities for intelligent music production.
Jun 17, 2026 1 source
Artificial Intelligence #music generation#preference alignment
TuneJury: Open Metric Improves Music Generation Preference Alignment
Researchers introduce TuneJury, an open metric for improving music generation preference alignment. The model predicts preference scores from text prompts and audio clips, trained on diverse human-preference labels, and supports data filtering and post-hoc calibration.
Jun 16, 2026 1 source