论文标题
MOS预测系统的语音表示形式的比较
Comparison of Speech Representations for the MOS Prediction System
论文作者
论文摘要
已经研究了预测听众平均意见评分（MOS）的自动方法，以确保文本到语音系统的质量。许多先前的研究都集中在建筑进步（例如MBNET，LDNET等）上，以更有效的方式捕获光谱特征与MOS之间的关系，并达到了高准确性。但是，在概括能力方面的最佳表示仍然很大程度上仍然未知。为此，我们将WAV2VEC框架获得的自我监督学习（SSL）特征的性能与光谱特征（例如光谱图和Melspectrogram的幅度）的性能进行了比较。此外，我们建议将SSL功能和功能结合起来，我们认为我们认为将基本信息保留到自动MOS上，以相互补偿其缺点。我们对从过去的暴风雪和语音转换挑战中收集的大规模听力测试语料库进行了全面的实验。我们发现，即使给定的地面真相并不总是可靠，WAV2VEC功能集也显示出最佳的概括。此外，我们发现这些组合表现最好，并分析了它们如何弥合光谱和WAV2VEC特征集之间的差距。
Automatic methods to predict Mean Opinion Score (MOS) of listeners have been researched to assure the quality of Text-to-Speech systems. Many previous studies focus on architectural advances (e.g. MBNet, LDNet, etc.) to capture relations between spectral features and MOS in a more effective way and achieved high accuracy. However, the optimal representation in terms of generalization capability still largely remains unknown. To this end, we compare the performance of Self-Supervised Learning (SSL) features obtained by the wav2vec framework to that of spectral features such as magnitude of spectrogram and melspectrogram. Moreover, we propose to combine the SSL features and features which we believe to retain essential information to the automatic MOS to compensate each other for their drawbacks. We conduct comprehensive experiments on a large-scale listening test corpus collected from past Blizzard and Voice Conversion Challenges. We found that the wav2vec feature set showed the best generalization even though the given ground-truth was not always reliable. Furthermore, we found that the combinations performed the best and analyzed how they bridged the gap between spectral and the wav2vec feature sets.
