arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.00344cs.SDcs.LGeess.AS
收藏

说话人相似度的自动评价

Automatic Evaluation of Speaker Similarity

Warsaw University of Technology(华沙理工大学);Amazon Research(亚马逊研究院)

Deja Kamil, Sanchez Ariadna, Roth Julian, Cotescu Marius

摘要:

我们介绍了一种新的自动评估方法的说话人相似性评估,这是符合人类的感知分数。现代神经文本到语音模型需要大量干净的训练数据,这就是为什么许多解决方案从单个说话者模型切换到基于许多不同说话者的示例训练的解决方案。多说话者模型带来了新的可能性,例如更快地创建新的声音,但也带来了新的问题-说话者泄漏,其中合成示例的说话者身份可能与目标说话者的身份不匹配。目前,发现这个问题的唯一方法是通过昂贵的感知评估。在这项工作中,我们提出了一个自动的方法来评估说话人的相似性。为此,我们扩展了最近的工作,说话人验证系统和评估不同的指标和说话人嵌入模型如何反映多个刺激与隐藏的参考和锚(MUSHRA)分数。我们的实验表明,我们可以训练一个模型来预测说话人相似度MUSHRA分数从说话人嵌入0.96的准确性和显着的相关性高达0.78皮尔逊分数在话语水平。

英文摘要:

We introduce a new automatic evaluation method for speaker similarity assessment, that is consistent with human perceptual scores. Modern neural text-to-speech models require a vast amount of clean training data, which is why many solutions switch from single speaker models to solutions trained on examples from many different speakers. Multi-speaker models bring new possibilities, such as a faster creation of new voices, but also a new problem - speaker leakage, where the speaker identity of a synthesized example might not match those of the target speaker. Currently, the only way to discover this issue is through costly perceptual evaluations. In this work, we propose an automatic method for assessment of speaker similarity. For that purpose, we extend the recent work on speaker verification systems and evaluate how different metrics and speaker embeddings models reflect Multiple Stimuli with Hidden Reference and Anchor (MUSHRA) scores. Our experiments show that we can train a model to predict speaker similarity MUSHRA scores from speaker embeddings with 0.96 accuracy and significant correlation up to 0.78 Pearson score at the utterance level.

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。

↑