Sorry, you need to enable JavaScript to visit this website.

Context-Aware Prosody Correction for Text-Based Speech Editing

Citation Author(s):
Max Morrison, Lucas Rencker, Nicholas J. Bryan, Juan-Pablo Caceres, Bryan Pardo
Submitted by:
Max Morrison
Last updated:
27 June 2021 - 1:49pm
Document Type:
Document Year:
Max Morrison


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.

0 users have voted: