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 2310.02640eess.AS
收藏

2023年VoiceMOS挑战赛:面向多领域的零样本主观语音质量预测

The VoiceMOS Challenge 2023: Zero-shot Subjective Speech Quality Prediction for Multiple Domains

Erica Cooper, Wen-Chin Huang, Yu Tsao, Hsin-Min Wang, Tomoki Toda, Junichi Yamagishi

AI总结:

第二届VoiceMOS挑战赛聚焦多场景零样本跨域语音MOS预测,设三个赛道,10支队伍参赛,发现法语文语合成子赛道可预测性差异大、歌声转换样本预测难度低于预期,证实多数据集与听众信息训练有效。

摘要:

我们介绍第二届VoiceMOS挑战赛,这是一项旨在推动合成与处理语音的平均意见得分(MOS)自动预测研究的学术活动。本届赛事聚焦真实场景下极具挑战性的零样本跨域MOS预测,设置三个赛道对应三种不同的语音评估场景。来自7个国家的产业界与学术界共10支队伍参赛。我们意外发现,法语文本转语音合成的两个子赛道在可预测性上差异显著,且歌声转换样本的预测难度并未如预期般高。训练过程中使用多样化数据集与听众信息被证实是有效的方法。

英文摘要:

We present the second edition of the VoiceMOS Challenge, a scientific event that aims to promote the study of automatic prediction of the mean opinion score (MOS) of synthesized and processed speech. This year, we emphasize real-world and challenging zero-shot out-of-domain MOS prediction with three tracks for three different voice evaluation scenarios. Ten teams from industry and academia in seven different countries participated. Surprisingly, we found that the two sub-tracks of French text-to-speech synthesis had large differences in their predictability, and that singing voice-converted samples were not as difficult to predict as we had expected. Use of diverse datasets and listener information during training appeared to be successful approaches.

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。

↑