一作ICML 2026Poster
Scaling Transformers for End-to-End Discrete Audio Tokenization
Yitian Gong · Kuangwei Chen · Zhaoye Fei · Xiaogui Yang · Ke Chen · Yang Wang · Kexin Huang · Mingshu Chen · Ruixiao Li · Qinyuan Cheng · Shimin Li · Xipeng Qiu
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。
Yitian Gong · Kuangwei Chen · Zhaoye Fei · Xiaogui Yang · Ke Chen · Yang Wang · Kexin Huang · Mingshu Chen · Ruixiao Li · Qinyuan Cheng · Shimin Li · Xipeng Qiu
Yitian Gong · Luozhijie Jin · Kuangwei Chen · Dong Zhang · Ruifan Deng · Xiaogui Yang · Xin Zhang · Zhaoye Fei · Qinyuan Cheng · Shimin Li · Xipeng Qiu
Speech codecs provide an important interface between continuous speech signals and large language models. An ideal codec for speech language models should not only preserve acoustic information but also capture rich semantic information. However, existing codecs struggle to balance these objectiv...