A unified comparison of six LM-based generative speech enhancement paradigms finds continuous non-autoregressive (CNAR) modeling best, and auxiliary-loss fine-tuning improves DNSMOS, NISQA, PESQ, and POLQA across all six.
Networks In the proposed SE models, the pretrained 16 kHzDAC[25] and WavLM[26] weights are adopted
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codec
A unified comparison of six LM-based generative speech enhancement paradigms finds continuous non-autoregressive (CNAR) modeling best, and auxiliary-loss fine-tuning improves DNSMOS, NISQA, PESQ, and POLQA across all six.