A multi-metric learned quality model (Uni-VERSA-Ext) is used as a differentiable training loss for speech enhancement, with a regularization term to prevent adversarial exploitation.
URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement Competition
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
The Mean Opinion Score (MOS) is fundamental to speech quality assessment. However, its acquisition requires significant human annotation. Although deep neural network approaches, such as DNSMOS and UTMOS, have been developed to predict MOS to avoid this issue, they often suffer from insufficient training data. Recognizing that the comparison of speech enhancement (SE) systems prioritizes a reliable system comparison over absolute scores, we propose URGENT-PK, a novel ranking approach leveraging pairwise comparisons. URGENT-PK takes homologous enhanced speech pairs as input to predict relative quality rankings. This pairwise paradigm efficiently utilizes limited training data, as all pairwise permutations of multiple systems constitute a training instance. Experiments across multiple open test sets demonstrate URGENT-PK's superior system-level ranking performance over state-of-the-art baselines, despite its simple network architecture and limited training data.
citation-role summary
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Improving Speech Enhancement with Multi-Metric Supervision from Learned Quality Assessment
A multi-metric learned quality model (Uni-VERSA-Ext) is used as a differentiable training loss for speech enhancement, with a regularization term to prevent adversarial exploitation.