Current singing voice synthesis models fail to differentiate musical genres, defaulting to pop-like output regardless of input genre, unless given genre-specific fine-tuning data.
Muskits: an End-to-end Music Processing Toolkit for Singing V oice Synthesis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MMGenre: Benchmarking Singing Voice Synthesis across Multiple Musical Genres
Current singing voice synthesis models fail to differentiate musical genres, defaulting to pop-like output regardless of input genre, unless given genre-specific fine-tuning data.