DDOS：一个利用领域自适应预训练和意见分数分布的MOS预测框架
DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores
摘要：
平均意见得分（MOS）是语音合成系统的一个典型的主观评价指标。由于收集MOS是耗时的，如果有精确的MOS预测模型进行自动评估，这将是可取的。在这项工作中，我们提出了DDOS，一种新的MOS预测模型。DDOS利用域自适应预训练来进一步预训练合成语音的自监督学习模型。并增加了一个建议的模块来模拟每个话语的意见得分分布。与建议的组件，DDOS优于以前的作品BVCC数据集。BC2019数据集上的zero shot传输结果得到显著改善。DDOS还在Interspeech 2022 VoiceMOS挑战赛中获得系统级评分第二名。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
