arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.02249eess.AS
收藏

语音合成质量预测的深度学习MOS预测器比较

A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality

Alessandro Ragano, Emmanouil Benetos, Michael Chinen, Helard B. Martinez, Chandan K. A. Reddy, Jan Skoglund, Andrew Hines

AI总结:

本文基于VoiceMOS挑战数据集评估了wav2vec 2.0和NISQA等MOS预测器,发现SSL模型表现更优,并指出仅靠统计性能不足以给模型排名,数据中的潜在问题会偏差评估结果。

摘要:

随着监督和自监督学习(SSL)MOS预测器的发展,语音合成质量预测取得了显著进展,但与数据相关的一些方面仍不明确,需要进一步研究。本文评估了基于wav2vec 2.0和NISQA语音质量预测模型的几种MOS预测器,以探讨训练数据的作用、系统类型的影响以及跨域特征在SSL模型中的角色。我们的评估基于VoiceMOS挑战数据集。结果表明,与监督模型相比,基于SSL的模型表现出最高的相关性和最低的均方误差。本研究的关键点是,仅对MOS预测器的统计性能进行基准测试不足以对模型进行排名,因为数据中隐藏的潜在问题可能会使评估性能产生偏差。

英文摘要:

Speech synthesis quality prediction has made remarkable progress with the development of supervised and self-supervised learning (SSL) MOS predictors but some aspects related to the data are still unclear and require further study. In this paper, we evaluate several MOS predictors based on wav2vec 2.0 and the NISQA speech quality prediction model to explore the role of the training data, the influence of the system type, and the role of cross-domain features in SSL models. Our evaluation is based on the VoiceMOS challenge dataset. Results show that SSL-based models show the highest correlation and lowest mean squared error compared to supervised models. The key point of this study is that benchmarking the statistical performance of MOS predictors alone is not sufficient to rank models since potential issues hidden in the data could bias the evaluated performances.

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。

↑