pith. sign in

Preference alignment improves language model- based TTS,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.SD 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Imitation Learning for Elder-Facing Speech Synthesis

cs.SD · 2026-06-19 · unverdicted · novelty 5.0

An imitation learning approach with two-stage on-policy reward learning enhances TTS for elderly listeners and outperforms standard GRPO and supervised baselines.

citing papers explorer

Showing 1 of 1 citing paper.

  • Imitation Learning for Elder-Facing Speech Synthesis cs.SD · 2026-06-19 · unverdicted · none · ref 23

    An imitation learning approach with two-stage on-policy reward learning enhances TTS for elderly listeners and outperforms standard GRPO and supervised baselines.