mlsanityData to 7 Oct 2026

MOSNet: Deep Learning based Objective Assessment for Voice Conversion

arXiv 1904.08352 ↗First posted 17 Apr 2019cs.SD cs.LG eess.AScited by 126

Not on the map. Why?

Abstract (arXiv)

Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In this paper, we propose deep learning-based assessment models to predict human ratings of converted speech. We adopt the convolutional and recurrent neural network models to build a mean opinion score (MOS) predictor, termed as MOSNet. The proposed models are tested on large-scale listening test results of the Voice Conversion Challenge (VCC) 2018. Experimental results show that the predicted scores of the proposed MOSNet are highly correlated with human MOS ratings at the system level while being fairly correlated with human MOS ratings at the utterance level. Meanwhile, we have modified MOSNet to predict the similarity scores, and the preliminary results show that the predicted scores are also fairly correlated with human ratings. These results confirm that the proposed models could be used as a computational evaluator to measure the MOS of VC systems to reduce the need for expensive human rating.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 16; 2022: 29; 2023: 22; 2024: 15; 2025: 18; 2026: 25.

126 papers.

Sort:

By area:

  1. 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 151
  2. 2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 116
  3. 2024The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speechcited by 78
  4. 2023Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation taskscited by 71
  5. 2021StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversioncited by 57
  6. 2022HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancementcited by 49
  7. 2023VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matchingcited by 49
  8. 2022Few-Shot Audio-Visual Learning of Environment Acousticscited by 48
  9. 2024Towards Robust Speech Representation Learning for Thousands of Languagescited by 48
  10. 2024Scaling Transformers for Low-Bitrate High-Quality Speech Codingcited by 48
  11. 2022Visual Acoustic Matchingcited by 45
  12. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
38 more
  1. 2021Deep Learning Based Assessment of Synthetic Speech Naturalnesscited by 35
  2. 2021Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Featurescited by 32
  3. 2025Audio Large Language Models Can Be Descriptive Speech Quality Evaluatorscited by 25
  4. 2021LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speechcited by 24
  5. 2021Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speechcited by 22
  6. 2021Utilizing Self-supervised Representations for MOS Predictioncited by 20
  7. 2025AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluationcited by 20
  8. 2022SpeechLMScore: Evaluating speech generation using speech language modelcited by 19
  9. 2022SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesiscited by 18
  10. 2024Measuring the Accuracy of Automatic Speech Recognition Solutionscited by 15
  11. 2025Watermarking Autoregressive Image Generationcited by 15
  12. 2024Enabling Auditory Large Language Models for Automatic Speech Quality Evaluationcited by 13
  13. 2023Translatotron 3: Speech to Speech Translation with Monolingual Datacited by 12
  14. 2021Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problemcited by 11
  15. 2022Fusion of Self-supervised Learned Models for MOS Predictioncited by 10
  16. 2022SQuId: Measuring Speech Naturalness in Many Languagescited by 10
  17. 2025From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speechcited by 9
  18. 2024Self-Supervised Audio-Visual Soundscape Stylizationcited by 8
  19. 2021InQSS: a speech intelligibility and quality assessment model using a multi-task learning networkcited by 7
  20. 2021Training Robust Zero-Shot Voice Conversion Models with Self-supervised Featurescited by 7
  21. 2022DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scorescited by 7
  22. 2023MOSPC: MOS Prediction Based on Pairwise Comparisoncited by 7
  23. 2024Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speechcited by 7
  24. 2025TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systemscited by 7
  25. 2022Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graphcited by 6
  26. 2022Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Reviewcited by 6
  27. 2022Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatarcited by 6
  28. 2023A multimodal dynamical variational autoencoder for audiovisual speech representation learningcited by 6
  29. 2025Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learningcited by 6
  30. 2022ECAPA-TDNN for Multi-speaker Text-to-speech Synthesiscited by 5
  31. 2022A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesiscited by 5
  32. 2022Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learningcited by 5
  33. 2021SVSNet: An End-to-end Speaker Voice Similarity Assessment Modelcited by 4
  34. 2021HASA-net: A non-intrusive hearing-aid speech assessment networkcited by 4
  35. 2023Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Studycited by 4
  36. 2023Towards Practical and Efficient Image-to-Speech Captioning with Vision-Language Pre-training and Multi-modal Tokenscited by 4
  37. 2024TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languagescited by 4
  38. 2024Optimal Transport Maps are Good Voice Converterscited by 4

50 most cited of 126 All 126 (JSON)