Automated TTS evaluators, both MOS predictors and Audio-LLM judges, systematically fail to detect most linguistically grounded speech errors, with MOS predictors collapsing onto signal-level artifacts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions
Automated TTS evaluators, both MOS predictors and Audio-LLM judges, systematically fail to detect most linguistically grounded speech errors, with MOS predictors collapsing onto signal-level artifacts.