By decomposing spectrogram reconstruction into a fixed pseudo-inverse range-space step and a learned null-space detail step, RNDVoC reaches near-BigVGAN quality with about 3% of the parameters and a 10x CPU speed-up.
Neural Vocoders as Speech Enhancers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: \textit{Can a model designed for one task's rank degradation be adapted for the other?} and \textit{Is it possible to address both tasks using a unified model?} Our empirical findings demonstrate that existing speech enhancement models can be successfully trained to perform vocoding tasks, and a single model, when jointly trained, can effectively handle both tasks with performance comparable to separately trained models. These results suggest that speech enhancement and neural vocoding can be unified under a broader framework of speech restoration. Code: https://github.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers.
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning Neural Vocoder from Range-Null Space Decomposition
By decomposing spectrogram reconstruction into a fixed pseudo-inverse range-space step and a learned null-space detail step, RNDVoC reaches near-BigVGAN quality with about 3% of the parameters and a 10x CPU speed-up.