Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models

arXiv:2610.40505 · eess.AS, cs.CL, cs.LG, cs.SD · Submitted 2026-10-29 · Read on arXiv

eess.AS, cs.CL, cs.LG, cs.SD

Submitted: 2026-10-29

Updated: 2026-10-29

Comments: Under review

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Related papers