mlsanityData to 19 Oct 2026

The VoiceMOS Challenge 2026: Evaluating Speech Enhancement, Emotional TTS and Accented TTS Systems

arXiv 2609.13792 ↗First posted 12 Sep 2026cs.SD eess.AScited by 0

On the map: Speech and audio language models → Vocoders and speech synthesis

Abstract (arXiv)

We present the results of the VoiceMOS Challenge 2026, the fifth edition of a scientific challenge on automatic prediction of subjective speech assessments. After expanding the scope to music and general audio in 2025, we refocused the evaluation target on speech and organized three tracks: prediction of absolute and comparative category ratings for enhanced speech, prediction of naturalness and emotion-related tasks for emotional text-to-speech systems, and prediction of speaker and accent similarity for codec-based speech synthesis systems. The challenge attracted a total of 18 teams worldwide, with most teams successfully surpassing the provided baselines. We summarize the challenge results, representative top-performing systems, participant feedback, and directions for future editions.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models. Builds on 25 of its 26 references that are in the map. First posted on arXiv 12 Sep 2026.

Builds on

25 of 26 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accents15 Mar
  2. 2021How do Voices from Past Speech Synthesis Challenges Compare Today?5 May

Other references · 23

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,661
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 4,385
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,762
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 2,135
  5. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 980
  6. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 552
  7. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 270
  8. 2023emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representationcited by 263
  9. 2023MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Trainingcited by 191
  10. 2021Emotional Voice Conversion: Theory, Databases and ESDcited by 146
  11. 2022DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speechcited by 80
  12. 2022The VoiceMOS Challenge 2022cited by 79
11 more
  1. 2024URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancementcited by 44
  2. 2021LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speechcited by 32
  3. 2025Interspeech 2025 URGENT Speech Enhancement Challengecited by 30
  4. 2024The VoiceMOS Challenge 2024: Beyond Speech Quality Predictioncited by 23
  5. 2023The VoiceMOS Challenge 2023: Zero-shot Subjective Speech Quality Prediction for Multiple Domainscited by 17
  6. 2021InQSS: a speech intelligibility and quality assessment model using a multi-task learning networkcited by 13
  7. 2024VoxSim: A perceptual voice similarity datasetcited by 13
  8. 2025The AudioMOS Challenge 2025cited by 9
  9. 2025SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessmentcited by 9
  10. 2026ICASSP 2026 URGENT Speech Enhancement Challengecited by 7
  11. 2026UrgentMOS: Unified Multi-Metric and Preference Learning for Robust Speech Quality Assessmentcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge
  2. 2025A Dataset for Automatic Assessment of TTS Quality in Spanish
  3. 2022SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
  4. 2026Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study
  5. 2025Objective Evaluation of Prosody and Intelligibility in Speech Synthesis via Conditional Prediction of Discrete Tokens
  6. 2026Improving Predicted MOS Scores, Not Perceived Quality: Multi-Predictor Test-Time Optimization of Enhanced Speech
  7. 2023EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech
  8. 2026Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions