一作ICLR 2026Poster· Applications / Language, Speech and Dialog
TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
Liang-Hsuan Tseng · Yi-Chang Chen · Kuan Lee · Da-shan Shiu · Hung-yi Lee
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。
Liang-Hsuan Tseng · Yi-Chang Chen · Kuan Lee · Da-shan Shiu · Hung-yi Lee
Chan-Jan Hsu · Liang-Hsuan Tseng · Yi-Cheng Lin · Yen-Chun Kuo · Ju-Chieh Chou · Kai-Wei Chang · Hung-yi Lee · Carlos Busso
Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior literature, these models are often evaluated using “global t...