mlsanityData to 14 Oct 2026

SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction

arXiv 2506.02082 ↗First posted 2 Jun 2025cs.SD cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Speech quality assessment is a critical process in selecting text-to-speech synthesis (TTS) or voice conversion models. Evaluation of voice synthesis can be done using objective metrics or subjective metrics. Although there are many objective metrics like the Perceptual Evaluation of Speech Quality (PESQ), Perceptual Objective Listening Quality Assessment (POLQA) or Short-Time Objective Intelligibility (STOI) but none of them is feasible in selecting the best model. On the other hand subjective metric like Mean Opinion Score is highly reliable but it requires a lot of manual efforts and are time-consuming. To counter the issues in MOS Evaluation, we have developed a novel model, Speaker Agnostic Latent Features (SALF)-Mean Opinion Score (MOS) which is a small-sized, end-to-end, highly generalized and scalable model for predicting MOS score on a scale of 5. We use the sequences of convolutions and stack them to get the latent features of the audio samples to get the best state-of-the-art results based on mean squared error (MSE), Linear Concordance Correlation coefficient (LCC), Spearman Rank Correlation Coefficient (SRCC) and Kendall Rank Correlation Coefficient (KTAU).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 27 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

22 of 27 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  5. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 390
  6. 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 188
  7. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 127
  8. 2018The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methodscited by 68
  9. 2022The VoiceMOS Challenge 2022cited by 57
  10. 2018Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTMcited by 37
  11. 2021MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Networkcited by 37
  12. 2021Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Featurescited by 33
10 more
  1. 2021LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speechcited by 24
  2. 2016AutoMOS: Learning a non-intrusive assessor of naturalness-of-speechcited by 22
  3. 2022SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesiscited by 18
  4. 2022Speech Quality Assessment through MOS using Non-Matching Referencescited by 16
  5. 2022Fusion of Self-supervised Learned Models for MOS Predictioncited by 10
  6. 2021InQSS: a speech intelligibility and quality assessment model using a multi-task learning networkcited by 7
  7. 2022DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scorescited by 7
  8. 2023MOSPC: MOS Prediction Based on Pairwise Comparisoncited by 7
  9. 2023LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancementcited by 4
  10. 2023Evaluation of Speech Representations for MOS predictioncited by 2

Built on by

Not cited yet.