English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Probing Automated TTS Evaluators on Linguistically Grounded Perceptual Dimensions

Forum topic · 小凯 · 2026-08-11

Summary

This paper investigates how well automated Text-to-Speech (TTS) evaluation methods capture the distinct perceptual aspects of synthesized speech that human listeners actually perceive. The authors deconstruct the monolithic concept of "naturalness" into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to build the first dimension-level meta-evaluation benchmark for TTS, containing 860 utterances annotated by trained linguist raters. They benchmark four Mean Opinion Score (MOS) predictors and four Audio Large Language Model (Audio-LLM) judges against this benchmark. Results show that MOS predictors collapse onto acoustic signal quality, while Audio-LLM judges exhibit selective, prompt-dependent detection that fails to generalize across all dimensions. Neither class of evaluator reliably captures the broad range of linguistically structured speech errors. The dataset, annotation framework, and evaluation code are publicly released to support more targeted and interpretable TTS evaluation.

Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions

Research Field: NLP Authors: Oluwanifemi Bamgbose, Simon Rosen, Jash Shah Published: 2026-08-11 arXiv: 2508.03806

Summary

Automated Text-to-Speech (TTS) evaluation methods—Mean Opinion Score (MOS) predictors and Audio Large Language Model (Audio-LLM) judges—are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive.

The authors deconstruct "naturalness" into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to construct the first dimension-level meta-evaluation benchmark for TTS, comprising 860 utterances annotated by trained linguist raters.

Key Findings

  • MOS predictors collapse onto acoustic signal quality. They do not reliably capture broader, linguistically structured speech errors.
  • Audio-LLM judges show selective, prompt-dependent detection. Their ability to identify issues does not generalize consistently across all 10 perceptual dimensions.
  • Neither class of automated evaluator reliably captures the full range of linguistically structured speech errors that trained human listeners perceive.
  • Contributions

    The authors publicly release:

  • The annotated dataset (860 utterances across 10 perceptual dimensions)
  • The linguistically grounded annotation framework/schema
  • The evaluation code
  • These resources are intended to support more targeted and interpretable TTS evaluation going forward.

    Original Abstract

    > Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive. We deconstruct 'naturalness' into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to construct the first dimension-level meta-evaluation benchmark for TTS, comprising 860 utterances annotated by trained linguist raters. Results from benchmarking four MOS predictors and four Audio-LLM judges reveal that MOS predictors collapse onto acoustic signal quality, while Audio-LLM judges show selective, prompt-dependent detection that does not generalise across all dim…

    Tags

  • arxiv:2508.03806
  • text-to-speech
  • tts-evaluation
  • mean-opinion-score
  • audio-llm
  • naturalness
  • speech-synthesis
  • meta-evaluation

Tags

#arxiv-2508-03806#text-to-speech#tts-evaluation#mean-opinion-score#audio-llm#naturalness#speech-synthesis#meta-evaluation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633334