arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.14725cs.SD
收藏

vTTS:视觉文本到语音

vTTS: visual-text to speech

The University of Tokyo(东京大学);Nara Institute of Science and Technology(奈良先端科学技术大学院大学)

Yoshifumi Nakano, Takaaki Saeki, Shinnosuke Takamichi, Katsuhito Sudoh, Hiroshi Saruwatari

摘要:

本文提出了视觉文本到语音(vTTS),一种从视觉文本合成语音的方法(即,文本作为图像)。传统的TTS将音素或字符转换为离散的符号,并从它们合成语音波形,从而失去了字符本质上具有的视觉特征。因此,我们的方法不是从离散符号而是从视觉文本合成语音。建议vTTS提取视觉特征与卷积神经网络,然后生成声学特征与非自回归模型的启发FastSpeech2。实验结果表明:1)vTTS能够生成与传统TTS相当或更好的自然度的语音,2)它可以将视觉文本中的强调和情感属性转换为语音,而无需额外的标签和架构,3)它可以从看不见的和罕见的字符合成比传统TTS更自然和可理解的语音。

英文摘要:

This paper proposes visual-text to speech (vTTS), a method for synthesizing speech from visual text (i.e., text as an image). Conventional TTS converts phonemes or characters into discrete symbols and synthesizes a speech waveform from them, thus losing the visual features that the characters essentially have. Therefore, our method synthesizes speech not from discrete symbols but from visual text. The proposed vTTS extracts visual features with a convolutional neural network and then generates acoustic features with a non-autoregressive model inspired by FastSpeech2. Experimental results show that 1) vTTS is capable of generating speech with naturalness comparable to or better than a conventional TTS, 2) it can transfer emphasis and emotion attributes in visual text to speech without additional labels and architectures, and 3) it can synthesize more natural and intelligible speech from unseen and rare characters than conventional TTS.

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。

↑