使用神经 HMM 的韵律可控自发型 TTS
Prosody-controllable spontaneous TTS with neural HMMs
AI总结：
本文在基于神经 HMM 的 TTS 系统中加入话语级韵律控制，利用小规模不规则自发语音数据实现稳定单调对齐，并验证其控制准确、音质不降且可合成两类吱嘎声。
摘要：
自发言语具有许多情感和语用功能，在 TTS 中对其建模既有趣又富有挑战性。然而，自发言语中存在弱化发音、填充词、重复以及其他不流畅现象，使文本与声学特征之间的对齐程度低于朗读言语，这对基于注意力的 TTS 构成问题。我们提出一种 TTS 架构，能够从规模较小且不规则的数据集中快速学习说话，同时再现自发言语中丰富多样的表达现象。具体而言，我们在一个现有的基于神经 HMM 的 TTS 系统中加入话语级韵律控制；该系统能够为自发言语实现稳定、单调的对齐。我们客观评估了控制准确性，并开展感知测试，结果表明韵律控制不会降低合成质量。为了展示结合韵律控制与生态有效数据来再现复杂自发现象的能力，我们评估了该系统合成两种 creaky voice（吱嘎声/紧喉嗓音）的能力。音频示例可在 https://www.speech.kth.se/tts-demos/prosodic-hmm/ 获取。
英文摘要：
Spontaneous speech has many affective and pragmatic functions that are interesting and challenging to model in TTS. However, the presence of reduced articulation, fillers, repetitions, and other disfluencies in spontaneous speech make the text and acoustics less aligned than in read speech, which is problematic for attention-based TTS. We propose a TTS architecture that can rapidly learn to speak from small and irregular datasets, while also reproducing the diversity of expressive phenomena present in spontaneous speech. Specifically, we add utterance-level prosody control to an existing neural HMM-based TTS system which is capable of stable, monotonic alignments for spontaneous speech. We objectively evaluate control accuracy and perform perceptual tests that demonstrate that prosody control does not degrade synthesis quality. To exemplify the power of combining prosody control and ecologically valid data for reproducing intricate spontaneous speech phenomena, we evaluate the system's capability of synthesizing two types of creaky voice. Audio samples are available at https://www.speech.kth.se/tts-demos/prosodic-hmm/
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。
