SpeechRefiner, a conformer-based conditional flow matching model, improves SIGMOS perceptual quality scores on speech processed by various front-ends, including unseen systems.
RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper introduces our repairing and denoising network (RaD-Net) for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. We extend our previous framework based on a two-stage network and propose an upgraded model. Specifically, we replace the repairing network with COM-Net from TEA-PSE. In addition, multi-resolution discriminators and multi-band discriminators are adopted in the training stage. Finally, we use a three-step training strategy to optimize our model. We submit two models with different sets of parameters to meet the RTF requirement of the two tracks. According to the official results, the proposed systems rank 2nd in track 1 and 3rd in track 2.
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms
SpeechRefiner, a conformer-based conditional flow matching model, improves SIGMOS perceptual quality scores on speech processed by various front-ends, including unseen systems.