一作ICML 2026Poster· Deep Learning / Other Representation Learning
Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
Hongfei Du · Jiacheng Shi · Sidi Lu · Gang Zhou · Ashley Gao
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Hongfei Du · Jiacheng Shi · Sidi Lu · Gang Zhou · Ashley Gao
Jiacheng Shi · Hongfei Du · Xinyuan Song · Y. Alicia Hong · Yanfu Zhang · Ashley Gao
Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acoustic reconstruction, leaving emotion expressiveness insufficiently modeled at the representation level. We propose an em...