While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i) ignorance of cross-sentence contextual information, and ii) high computation and memory cost for long-form synthesis. To address these issues, this work develops a lightweight yet effective TTS system, ContextSpeech. Specifically, we first design a memory-cached recurrence mechanism to incorporate global text and speech context into sentence encoding. Then we construct hierarchically-structured textual semantics to broaden the scope for global context enhancement. Additionally, we integrate linearized self-attention to improve model efficiency. Experiments show that ContextSpeech significantly improves the voice quality and prosody expressiveness in paragraph reading with competitive model efficiency. Audio samples are available at: https://contextspeech.github.io/demo/

翻译：尽管最先进的文本转语音系统能在句子级别生成非常自然的语音，但它们在段落/长文本朗读的语音生成中仍面临巨大挑战。这些缺陷源于：i）忽略跨句子上下文信息，以及ii）长文本合成的高计算与内存成本。为解决这些问题，本工作开发了一个轻量级且高效的TTS系统ContextSpeech。具体而言，我们首先设计了一种内存缓存循环机制，将全局文本与语音上下文融入句子编码中。随后构建了层次结构的文本语义，以拓宽全局上下文增强的范围。此外，我们集成了线性化自注意力机制以提升模型效率。实验表明，ContextSpeech在段落朗读中显著提升了语音质量与韵律表现力，同时保持了具有竞争力的模型效率。音频样本可于 https://contextspeech.github.io/demo/ 获取。