1 citations · 1 across the 4 of their papers we have counts for
Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
Frame-Wise Streaming for Efficient Learned Speech Compression
Yuhan Liu, Jun Xu, Fengxi Zhang +2
Speech compression is increasingly important in scenarios such as real-time and satellite communication. Neural codecs have shown superior Rate-Distortion (RD) performance over tra…
cs.SD2026
Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models
Yanda Li, Yuhan Liu, Zirui Song +3
Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be un…