arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.11673cs.SDcs.AIcs.CLcs.LGeess.AS
收藏

基于深度学习的合成语音自然度评价

Deep Learning Based Assessment of Synthetic Speech Naturalness

Gabriel Mittag, Sebastian Möller

摘要:

本文提出了一种新的合成语音自然度客观预测模型。它可用于评估文本到语音或语音转换系统和工作语言独立。该模型是端到端训练的,并且基于CNN-LSTM网络,该网络先前已被证明可以为语音质量估计提供良好的结果。我们在16个不同的数据集上训练和测试了这个模型,比如暴雪挑战赛和语音转换挑战赛。此外,我们表明,基于深度学习的自然度预测的可靠性可以通过迁移学习从基于客观POLQA分数训练的语音质量预测模型中得到提高。所提出的模型是公开的,可以,例如,用于评估不同的TTS系统配置。

英文摘要:

In this paper, we present a new objective prediction model for synthetic speech naturalness. It can be used to evaluate Text-To-Speech or Voice Conversion systems and works language independently. The model is trained end-to-end and based on a CNN-LSTM network that previously showed to give good results for speech quality estimation. We trained and tested the model on 16 different datasets, such as from the Blizzard Challenge and the Voice Conversion Challenge. Further, we show that the reliability of deep learning-based naturalness prediction can be improved by transfer learning from speech quality prediction models that are trained on objective POLQA scores. The proposed model is made publicly available and can, for example, be used to evaluate different TTS system configurations.

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。

↑