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 2110.03012eess.AScs.CL
收藏

并行神经网络TTS的加重控制

Emphasis control for parallel neural TTS

Apple(苹果公司)

Shreyas Seshadri, Tuomo Raitio, Dan Castellani, Jiangchuan Li

摘要:

最近的并行神经文本到语音(TTS)合成方法能够产生语音高保真度,同时保持高性能。然而,这些系统往往缺乏对输出韵律的控制,从而限制了给定文本的语义信息。本文提出了一种分层并行神经TTS系统的韵律强调控制学习的潜在空间,直接对应于一个重点的变化。比较潜在空间的三个候选特征:1)句子中的词内的音高和持续时间的方差,2)从音高、能量和持续时间计算的基于小波的特征,以及3)上述两种方法的学习组合。在推理时,通过增加给定词的潜在空间的特征值来实现词级韵律强调。实验表明,所有提出的方法都能够实现增加的重点,在整体质量损失不大的感觉。此外,在成对比较测试中,强调的话语比非强调的话语更受欢迎,这表明在现实世界中的应用前景。

英文摘要:

Recent parallel neural text-to-speech (TTS) synthesis methods are able to generate speech with high fidelity while maintaining high performance. However, these systems often lack control over the output prosody, thus restricting the semantic information conveyable for a given text. This paper proposes a hierarchical parallel neural TTS system for prosodic emphasis control by learning a latent space that directly corresponds to a change in emphasis. Three candidate features for the latent space are compared: 1) Variance of pitch and duration within words in a sentence, 2) Wavelet-based feature computed from pitch, energy, and duration, and 3) Learned combination of the two aforementioned approaches. At inference time, word-level prosodic emphasis is achieved by increasing the feature values of the latent space for the given words. Experiments show that all the proposed methods are able to achieve the perception of increased emphasis with little loss in overall quality. Moreover, emphasized utterances were preferred in a pairwise comparison test over the non-emphasized utterances, indicating promise for real-world applications.

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。

↑