arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.02373cs.SDeess.AS
收藏

过去语音合成挑战中的声音与今天相比如何?

How do Voices from Past Speech Synthesis Challenges Compare Today?

National Institute of Informatics(国立情报学研究所)

Erica Cooper, Junichi Yamagishi

摘要:

共同的挑战为使用标准化评价比较接受过共同数据培训的系统提供了一个场所,当数据和评价结果公开发布时,它们也为研究人员提供了宝贵的资源。暴雪挑战赛和语音转换挑战赛分别是文本到语音合成和扬声器转换的两个挑战赛,它们公开的系统样本和听力测试结果构成了多年来最先进的合成方法的历史记录。在本文中,我们重新审视了这些过去的挑战,并进行了大规模的听力测试与样本从许多挑战相结合。我们的目标是分析和比较大量系统的意见,以确定意见是否以及如何随着时间的推移而变化,并收集各种各样的合成样本及其评级的大规模数据集,以供进一步研究。我们发现,在系统层面上,原始结果与我们新的听力测试之间存在很强的相关性。我们还观察到扬声器的选择对合成质量的重要性。

英文摘要:

Shared challenges provide a venue for comparing systems trained on common data using a standardized evaluation, and they also provide an invaluable resource for researchers when the data and evaluation results are publicly released. The Blizzard Challenge and Voice Conversion Challenge are two such challenges for text-to-speech synthesis and for speaker conversion, respectively, and their publicly-available system samples and listening test results comprise a historical record of state-of-the-art synthesis methods over the years. In this paper, we revisit these past challenges and conduct a large-scale listening test with samples from many challenges combined. Our aims are to analyze and compare opinions of a large number of systems together, to determine whether and how opinions change over time, and to collect a large-scale dataset of a diverse variety of synthetic samples and their ratings for further research. We found strong correlations challenge by challenge at the system level between the original results and our new listening test. We also observed the importance of the choice of speaker on synthesis quality.

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。

↑