Adding a consistency loss between vocal-only and mixture encoder features during LoRA fine-tuning of Whisper improves lyrics transcription on music mixtures by a small but consistent margin, without needing source separation at inference.
PEFT on foundation models As ASR models get bigger, they require more and more com- putational resources which often may not be available for re- searchers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Enhancing Lyrics Transcription on Music Mixtures with Consistency Loss
Adding a consistency loss between vocal-only and mixture encoder features during LoRA fine-tuning of Whisper improves lyrics transcription on music mixtures by a small but consistent margin, without needing source separation at inference.