Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
机构 * Key Laboratory of Intelligent Information Processing Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所智能信息处理重点实验室) ; University of Chinese Academy of Sciences(中国科学院大学) ; Pattern Recognition Center, WeChat AI, Tencent Inc(腾讯人工智能研究院模式识别中心) ; School of Future Science and Engineering, Soochow University(苏州大学未来科学与工程学院)
专题命中 效率与部署 :language model(title,abstract);分类 cs.CL
Comments NeurIPS 2025; Demos and code are available at https://github.com/ictnlp/SLED-TTS