AI & ML
A Study on Improving Multi-class Audio Source Separation Via Decoupled CLAP Query Optimization and an Automated Data Engine
arXiv cs.SD0 views
arXiv:2610.10025v1 Announce Type: new Abstract: Language-queried audio source separation (LASS) enables extracting any sound source using natural language. However, adapting LASS models to application-specific sound classes is challenging due to noisy training data and limited semantic coverage of the CLAP-based control signals. We propose a framework comprised of an automated data engine for training-data curation and a two-stage optimization process for class-specific CLAP control signals. Our objective evaluations across seven sound classes show that data refinement and control signal optimization consistently improve source separation performance. Subjective evaluation with 17 participants further demonstrates perceptual improvements of the model trained with optimized control signals over baseline and similar commercial models.
Source：https://arxiv.org/abs/2610.10025PreviousBackdooring Acoustic Foundation Models for Physically Realizable TriggersNextCARES: A Controlled Synthetic Benchmark of Speaker Reactions to Sound
Related posts
Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
0arXiv stat.ML
Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary
0arXiv stat.ML
Spectral Condition for $\mu$P under Width-Depth Scaling
0arXiv stat.ML
A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems
0arXiv stat.ML
Who Gets Watched? Allocating Scarce Escalation Resources on Pediatric Wards with Neural Index Policies
0arXiv stat.ML
Minimax Alternating Regret for the Experts Problem and Online Convex Optimization
0arXiv stat.ML