Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model

作者：Ke Hu, Ehsan Hosseini-Asl, Chen Chen, Edresson Casanova, Subhankar Ghosh, Piotr Żelasko, Zhehuai Chen, Jason Li, Jagadeesh Balam, Boris Ginsburg · 年份：2025 · DOI：10.21437/interspeech.2025-874 · 被引用次数：6 · 研究领域：Speech Recognition and Synthesis、Speech and Audio Processing