Research
Test-time adaptation for speech enhancement with an autoregressive speech prior
arXiv:2609.03622v1 Announce Type: cross Abstract: Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models under mismatched acoustic conditions, without requirin
arXiv:2609.03622v1 Announce Type: cross Abstract: Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models under mismatched acoustic conditions, without requiring access to labeled target data. In this work, we propose a single-utterance TTA method that regularizes a pretrained speech enhancement model using an autoregressive prior trained on clean speech latent representations extracted from a neural audio codec. Adaptation is performed by minimizing the Kullback-Leibler divergence between the enhanced speech distribution and the clean speech prior. Experiments across multiple noisy speech datasets show consistent improvements in speech quality, particularly under training-testing noise mismatch conditions. Code and audio examples are available online.
Related
- On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
- PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement
- UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement
Source: arXiv cs.AI | 2026-09-04