Preprint Open access
ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent Geometry
Speech delivery varies with both the requested paralinguistic attribute and the linguistic content. We introduce ParaGeo, a matched-content decomposition of paralinguistic variation in a frozen speech language model. Synthesized audio tokens are replayed with a fixed listening prompt; pooled key/value (K/V) representat …