M2-CTTS: 端到端的多尺度、多模态会话文本到语音合成（英文版）

英文标题：M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis中文摘要：提出了一种多尺度，多模态会话文本到语音系统（M2-CTTS），用于综合利用历史会话并增强韵律表达，通过考虑文本和声学因素的粗粒度和细粒度建模，并混合细粒度上下文信息及声学特征，实现了更好的韵律表现和自然度。英文摘要：Conversational text-to-speech (TTS) aims to synthesize speech with properprosody of reply based on the historical conversation. However, it is still achallenge to comprehensively model the conversation, and a majority ofconversational TTS systems only focus on extracting global information and omi