2 papers
cs.CL2025
Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
Zhengrui Ma, Yang Feng, Chenze Shao +3
We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregres…
cs.CL2025
Overcoming Non-monotonicity in Transducer-based Streaming Generation
Zhengrui Ma, Yang Feng, Min Zhang
Streaming generation models are utilized across fields, with the Transducer architecture being popular in industrial applications. However, its input-synchronous decoding mechanism…