arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.03388eess.AScs.LGcs.SD
收藏

可控神经韵律合成

Controllable Neural Prosody Synthesis

Adobe Research(Adobe 研究院)

Max Morrison, Zeyu Jin, Justin Salamon, Nicholas J. Bryan, Gautham J. Mysore

摘要:

语音合成在神经声码器和神经韵律发生器的出现的推动下,最近在保真度方面有了显著的改进。然而,这些系统缺乏对韵律的直观用户控制,使得它们不能纠正韵律错误(例如,错位的重点和上下文不适当的情绪)或生成具有不同的说话者兴奋水平和情绪的韵律。我们解决这些限制与用户可控,上下文感知神经韵律发生器。给定一个真实的或合成的语音记录,我们的模型允许用户输入韵律约束的某些时间帧,并生成剩余的时间帧从输入文本和上下文韵律。我们还提出了一个音高移位神经声码器来修改输入语音,以匹配合成的韵律。通过客观和主观的评价,我们表明,我们可以成功地将用户控制到我们的韵律生成模型,而不牺牲合成语音的整体自然。

英文摘要:

Speech synthesis has recently seen significant improvements in fidelity, driven by the advent of neural vocoders and neural prosody generators. However, these systems lack intuitive user controls over prosody, making them unable to rectify prosody errors (e.g., misplaced emphases and contextually inappropriate emotions) or generate prosodies with diverse speaker excitement levels and emotions. We address these limitations with a user-controllable, context-aware neural prosody generator. Given a real or synthesized speech recording, our model allows a user to input prosody constraints for certain time frames and generates the remaining time frames from input text and contextual prosody. We also propose a pitch-shifting neural vocoder to modify input speech to match the synthesized prosody. Through objective and subjective evaluations we show that we can successfully incorporate user control into our prosody generation model without sacrificing the overall naturalness of the synthesized speech.

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。

↑