作者位次 #8/12ACL 2026Poster· Natural Language Processing
SAC : Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization
Wenxi Chen · Ruiqi Yan · Yushen Chen · Zhikang Niu · Ziyang Ma · Xiquan Li · Yuzhe Liang · Wenhanlin · Shunshun Yin · Ming Tao · Xinsheng Wang · Xie Chen
摘要
Speech codecs that convert continuous speech signals into discrete tokens have become essential for speech language models. However, existing codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understa...