Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

NeurIPSSpotlight2025

Authors: Tianrui Wang, Haoyu Wang, Meng Ge, Cheng Gong, Chunyu Qiang, Ziyang Ma, Zikang Huang, Guanrou Yang, Xiaobao Wang, EngSiong Chng, Xie Chen, Longbiao Wang, Jianwu Dang
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

While emotional text-to-speech (TTS) has made significant progress, most existing research remains limited to utterance-level emotional expression and fails to support word-level control…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

zero-shot control speech

← All NeurIPS 2025 Spotlight papers · Browse the whole archive