Preprint
Oct 2026
VoiceWeaver: Staged Learning of Structured Controls for Expressive Speech and Sound-Event Generation
VoiceWeaver addresses the problem of adding expressive and environmental controls to a speech generator with structured label prefixes and staged emotion-tone-event training in a shared text-audio model, while embedding decorrelation and attribute dropout regularize conditioning.
Xiao-Su Su, Yun Cao, Yi-Ping Ni et al.
· 0 citations