Ldnet: Unified Listener Dependent Modeling In MOS Prediction For Synthetic Speech
2021 · Wen-Chin Huang, Erica Cooper, Junichi Yamagishi, et al.
Abstract
An effective approach to automatically predict the subjective rating for synthetic speech is to train on a listening test dataset with human-annotated scores. Although each speech sample in the dataset is rated by several listeners, most previous works only used the mean score as the training target. In this work, we present LDNet, a unified framework for mean opinion score (MOS) prediction that predicts the listener-wise perceived quality given the input speech and the listener identity. We reflect recent advances in LD modeling, including design choices of the model architecture, and propose two inference methods that provide more stable results and efficient computation. We conduct systematic experiments on the voice conversion challenge (VCC) 2018 benchmark and a newly collected large-scale MOS dataset, providing an in-depth analysis of the proposed framework. Results show that the mean listener inference method is a better way to utilize the mean scores, whose effectiveness is mor
Authors
(none)
Tags
Stats
Related papers
- LE-SSL-MOS: Self-supervised Learning MOS Prediction With Listener Enhancement (2023)9.23
- Mosnet: Deep Learning Based Objective Assessment For Voice Conversion (2019)16.90
- Neural MOS Prediction For Synthesized Speech Using Multi-task Learning With Spoofing Detection And Spoofing Type Classification (2020)9.59
- DDOS: A MOS Prediction Framework Utilizing Domain Adaptive Pre-training And Distribution Of Opinion Scores (2022)9.03
- A Comparison Of Deep Learning MOS Predictors For Speech Synthesis Quality (2022)6.34
- Investigating Content-aware Neural Text-to-speech MOS Prediction Using Prosodic And Linguistic Features (2022)6.34
- Attention-based Speech Enhancement Using Human Quality Perception Modelling (2023)0.00
- SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations And Acoustic Features (2024)2.26