Context-Aware Prosody Correction for Text-Based Speech Editing
Abstract
Text-based speech editors expedite the process of editing speech recordings by permitting editing via intuitive cut, copy, and paste operations on a speech transcript. A major drawback of current systems, however, is that edited recordings often sound unnatural because of prosody mismatches around edited regions. In our work, we propose a new context-aware method for more natural sounding text-based editing of speech. To do so, we 1) use a series of neural networks to generate salient prosody features that are dependent on the prosody of speech surrounding the edit and amenable to fine-grained user control 2) use the generated features to control a standard pitch-shift and time-stretch method and 3) apply a denoising neural network to remove artifacts induced by the signal manipulation to yield a high-fidelity result. We evaluate our approach using a subjective listening test, provide a detailed comparative analysis, and conclude several interesting insights.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2021
- DOI:
- 10.48550/arXiv.2102.08328
- arXiv:
- arXiv:2102.08328
- Bibcode:
- 2021arXiv210208328M
- Keywords:
-
- Electrical Engineering and Systems Science - Audio and Speech Processing;
- Computer Science - Machine Learning;
- Computer Science - Sound
- E-Print:
- To appear in proceedings of ICASSP 2021