arXiv AI By Yoto Fujita, Simon Leglaive, Laurent Girin

Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations

Read the original on arXiv AI →

The paper introduces Masked Autoregressive Speech Enhancement (MARSE), a method that iteratively decodes masked clean speech frames using continuous latent representations from a neural audio codec (DAC). Unlike prior approaches that relied on discrete token representations, MARSE employs a Conformer model and explores various decoding policies to balance speech enhancement performance with computational cost. The authors provide audio examples and code online to demonstrate the method’s effectiveness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Sep 4

Test-time adaptation for speech enhancement with an autoregressive speech prior

The paper proposes a single‑utterance test‑time adaptation (TTA) method for speech enhancement that uses an autoregressive prior trained on clean speech latent representations from a neural audio codec. The adaptation regularizes a pretrained enhancement model by minimizing the Kullback‑Leibler divergence between the enhanced speech distribution and the clean speech prior. Experiments on multiple noisy speech datasets demonstrate consistent improvements in speech quality, especially when training and testing noise conditions differ.

By Sofiene Kammoun, Simon Leglaive, Xavier Alameda-Pineda, Timo Gerkmann
Hugging Face Trending Papers
Jun 3

CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding

Neural audio codecs are a key component of speech processing pipelines, compressing audio into discrete tokens for downstream modeling. However, existing codecs struggle to balance reconstruction quality with token efficiency, often encoding perceptually irrelevant information such as background noise and recording artifacts at the expense of linguistically and acoustically meaningful content.