TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems

Christoph Minixhofer, Ondrej Klejch, Peter Bell · Jun 24, 2025 · Citations: 0

Abstract

Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. Subjective metrics such as Mean Opinion Score (MOS) are not easily comparable between works. Objective metrics are frequently used, but rarely validated against subjective ones. Both kinds of metrics are challenged by recent TTS systems capable of producing synthetic speech indistinguishable from real speech. In this work, we introduce Text to Speech Distribution Score 2 (TTSDS2), a more robust and improved version of TTSDS. Across a range of domains and languages, it is the only one out of 16 compared metrics to correlate with a Spearman correlation above 0.50 for every domain and subjective score evaluated. We also release a range of resources for evaluating synthetic speech close to real speech: A dataset with over 11,000 subjective opinion score ratings; a pipeline for continually recreating a multilingual test dataset to avoid data leakage; and a continually updated benchmark for TTS in 14 languages.

HFEPX Relevance Assessment

This paper appears adjacent to HFEPX scope (human-feedback/eval), but does not show strong direct protocol evidence in metadata/abstract.

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: Multilingual
Extraction source: Persisted extraction

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.35
Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

spearman

Research Brief

Deterministic synthesis

Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 5, 2026, 3:23 AM · Grounded in abstract + metadata only

Key Takeaways

Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive.
In this work, we introduce Text to Speech Distribution Score 2 (TTSDS2), a more robust and improved version of TTSDS.

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Validate metric comparability (spearman).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive.
In this work, we introduce Text to Speech Distribution Score 2 (TTSDS2), a more robust and improved version of TTSDS.
We also release a range of resources for evaluating synthetic speech close to real speech: A dataset with over 11,000 subjective opinion score ratings; a pipeline for continually recreating a multilingual test dataset to avoid data leakage;…

Why It Matters For Eval

Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive.
We also release a range of resources for evaluating synthetic speech close to real speech: A dataset with over 11,000 subjective opinion score ratings; a pipeline for continually recreating a multilingual test dataset to avoid data leakage;…

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Pass: Evaluation mode is explicit

Detected: Automatic Metrics
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Pass: Metric reporting is present

Detected: spearman

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models Category Neighbor

Citations: 0 Relevance: 4.80
- Shared arXiv category (cs.SD, cs.CL)
Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems Category Neighbor

Citations: 0 Relevance: 2.95
- Shared arXiv category (cs.CL)
- Shared terminology (benchmark, evaluating, systems)
MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning Category Neighbor

Citations: 0 Relevance: 2.95
- Shared arXiv category (cs.CL)
- Shared terminology (benchmark, evaluating, systems)
According to Me: Long-Term Personalized Referential Memory QA Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (benchmark, systems)
ClinConsensus: A Consensus-Based Benchmark for Evaluating Chinese Medical LLMs across Difficulty Levels Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (benchmark, evaluating)
Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (evaluating, text)
FlashEvaluator: Expanding Search Space with Parallel Evaluation Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (evaluating, systems)
HateMirage: An Explainable Multi-Dimensional Dataset for Decoding Faux Hate and Subtle Online Abuse Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (benchmark, speech)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote