11 citations · 13 across the 6 of their papers we have counts for
Showing 2026 · cs.CLShow all
3 papers · 2 filters
cs.CL2026
Full-Duplex Speech Models Take the Floor When Asked, Not When Needed
Linkai Peng, Baorian Nuchged, Kaiqi Fu +1
Full-duplex speech models listen and speak at once, promising always-on assistants. Yet they must also decide when they should speak. Human listeners speak when addressed or when t…
cs.CL2026
Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models
Linkai Peng, Baorian Nuchged
Speech language models are increasingly evaluated on paralinguistic tasks by the accuracy of prompted answers, but answer accuracy combines failures at different stages of the audi…
cs.CL2026
Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models
Linkai Peng, Baorian Nuchged
Human speech is richly expressive, with prosody carrying linguistic and emotional information beyond the lexical content. A capable large audio-language model (audio-LLM) should th…