arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08328eess.AScs.LGcs.SD
收藏

基于文本的语音编辑中的上下文感知韵律校正

Context-Aware Prosody Correction for Text-Based Speech Editing

Adobe Research(奥多比研究院)

Max Morrison, Lucas Rencker, Zeyu Jin, Nicholas J. Bryan, Juan-Pablo Caceres, Bryan Pardo

摘要:

基于文本的语音编辑器通过允许经由对语音转录的直观剪切、复制和粘贴操作进行编辑来加快编辑语音记录的过程。然而,当前系统的一个主要缺点是,由于编辑区域周围的韵律不匹配,编辑的录音通常听起来不自然。在我们的工作中,我们提出了一个新的上下文感知的方法,更自然的声音基于文本的语音编辑。为此,我们1)使用一系列神经网络来生成显著的韵律特征,这些特征取决于编辑周围的语音韵律,并且可以进行细粒度的用户控制2)使用生成的特征来控制标准的音高偏移和时间拉伸方法3)应用去噪神经网络来去除由信号操纵引起的伪影,以产生高保真结果。我们使用主观听力测试来评估我们的方法,提供详细的比较分析,并得出一些有趣的见解。

英文摘要:

Text-based speech editors expedite the process of editing speech recordings by permitting editing via intuitive cut, copy, and paste operations on a speech transcript. A major drawback of current systems, however, is that edited recordings often sound unnatural because of prosody mismatches around edited regions. In our work, we propose a new context-aware method for more natural sounding text-based editing of speech. To do so, we 1) use a series of neural networks to generate salient prosody features that are dependent on the prosody of speech surrounding the edit and amenable to fine-grained user control 2) use the generated features to control a standard pitch-shift and time-stretch method and 3) apply a denoising neural network to remove artifacts induced by the signal manipulation to yield a high-fidelity result. We evaluate our approach using a subjective listening test, provide a detailed comparative analysis, and conclude several interesting insights.

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。

↑