Emotion Selectable End-to-End Text-based Speech Editing

In our previous work, we proposed the CampNet for end-to-end text-based speech editing, which can delete, replace and insert the speech at the word level by editing the transcription.

In this work, we propose Emo-CampNet, which can provide emotional options for generated speech on the basis of text-based speech editing, so as to make generated speech more expressive. This page shows the samples in the paper "Emotion Selectable End-to-End Text-based Speech Editing".

Experiments were based on VCTK and ESD . All test samples have not appeared in the training set and validation set.

Arxiv: https://arxiv.org/abs/2212.10191