 HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for
Expressive Long-form TTSAutomatic Speech Recognition & Understanding (ASRU), 2023 |
 MSStyleTTS: Multi-Scale Style Modeling with Hierarchical Context
Information for Expressive Speech SynthesisIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2023 |
 Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with
Acoustic and Textual ContextsIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in
Paragraph-based TTSIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2022 |
 Controllable Context-aware Conversational Speech SynthesisInterspeech (Interspeech), 2021 |
