周一晚：
TTS声码器：Speech Synthesis: Neural Waveform Generation I[Mon-1-5] (19:15-20:15)
VC：Voice Conversion and Adaptation I[Mon-2-7] (20:30-21:30)
歌声和多模态合成：Singing and Multimodal Synthesis[Mon-3-8] (21:45-22:45)
歌声音乐：Singing Voice Computing and Processing in Music[Mon-3-5] (21:45-22:45)
周二晚：
- TTS文本处理数据评价：Speech Synthesis: Text Processing, Data and Evaluation[Tue-1-7] (19:15-20:15)
语音翻译？多语种多模态学习：Speech Translation and multilingual/multimodal learning[Tue-1-1] (19:15-20:15)
周三晚：
TTS范式方法：Speech Synthesis Paradigms and Methods I[Wed-1-3] (19:15-20:15)
多语种：Bi- and multilinguality[Wed-1-10] (19:15-20:15)
- TTS多语种跨语言：Speech Synthesis: Multilingual and Cross-lingual approaches[Wed-2-11] (20:30-21:30)
TTS范式方法：Speech Synthesis Paradigms and Methods II[Wed-3-4] (21:45-22:45) - TTS 情感韵律：Speech Synthesis: Prosody and Emotion[Wed-3-10] (21:45-22:45)
多模态：Multimodal Speech Processing[Wed-3-12] (21:45-22:45)
说话人：Speaker Embedding[Wed-3-5] (21:45-22:45)
周四晚：
TTS声码器：Speech Synthesis: Neural Waveform Generation II[Thu-1-1] (19:15-20:15)
- 端到端TTS：Speech Synthesis: Toward End-to-End Synthesis[Thu-1-11] (19:15-20:15)
- TTS韵律建模：Speech Synthesis: Prosody Modeling[Thu-2-9] (20:30-21:30)
VC：Voice Conversion and Adaptation II[Thu-3-4] (21:45-22:45)
多语种code-switch的ASR：Multilingual and code-switched ASR[Thu-3-5] (21:45-22:45)
