mlsanityData to 7 Oct 2026

DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores

arXiv 2204.03219 ↗First posted 7 Apr 2022eess.AS cs.LG cs.SDcited by 7

Not on the map. Why?

Abstract (arXiv)

Mean opinion score (MOS) is a typical subjective evaluation metric for speech synthesis systems. Since collecting MOS is time-consuming, it would be desirable if there are accurate MOS prediction models for automatic evaluation. In this work, we propose DDOS, a novel MOS prediction model. DDOS utilizes domain adaptive pre-training to further pre-train self-supervised learning models on synthetic speech. And a proposed module is added to model the opinion score distribution of each utterance. With the proposed components, DDOS outperforms previous works on BVCC dataset. And the zero shot transfer result on BC2019 dataset is significantly improved. DDOS also wins second place in Interspeech 2022 VoiceMOS challenge in terms of system-level score.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 7 Apr 2022.

Builds on

20 of 29 references.

References · 20

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  4. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  6. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  7. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  8. 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 186
  9. 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 185
  10. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 148
  11. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 126
  12. 2020Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversioncited by 75
8 more
  1. 2021Generalization Ability of MOS Prediction Networkscited by 69
  2. 2018The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methodscited by 68
  3. 2022The VoiceMOS Challenge 2022cited by 57
  4. 2021MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Networkcited by 37
  5. 2021Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Featurescited by 32
  6. 2021LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speechcited by 24
  7. 2021Utilizing Self-supervised Representations for MOS Predictioncited by 20
  8. 2020Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissionscited by 19

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1; 2025: 2.

7 papers.

  1. 2023MOSPC: MOS Prediction Based on Pairwise Comparisoncited by 7
  2. 2024Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speechcited by 7
  3. 2023Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Predictioncited by 4
  4. 2023Evaluation of Speech Representations for MOS predictioncited by 2
  5. 2025APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speechcited by 2
  6. 2023MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Modulecited by 0
  7. 2025SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Predictioncited by 0