PrefSQA predicts speech quality via pairwise preferences with uncertainty-aware logits, impairment attention, and non-matching reference handling, showing gains mainly on refined high-quality datasets.
It is worth mentioning that these two datasets only contain pairs with matching speech content
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PrefSQA: Pairwise Preference Prediction for Speech Quality Assessment and the Critical Role of High Quality Datasets
PrefSQA predicts speech quality via pairwise preferences with uncertainty-aware logits, impairment attention, and non-matching reference handling, showing gains mainly on refined high-quality datasets.