GatherMOS uses LLMs as meta-evaluators to aggregate acoustic features and pseudo-labels for improved mean opinion score prediction in few-shot speech quality assessment.
Experimental setup The proposed approaches are evaluated on the V oiceBank- DEMAND dataset [15], which is also included in the test evaluation of the V oiceMOS Challenge 2024 [16]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language Models
GatherMOS uses LLMs as meta-evaluators to aggregate acoustic features and pseudo-labels for improved mean opinion score prediction in few-shot speech quality assessment.