Robust and fine-grained prosody control of end-to-end speech synthesis
This work addresses the need for expressive and emotional speech synthesis with precise control, offering incremental improvements in prosody manipulation for applications like text-to-speech systems.
The authors tackled the problem of controlling prosody in end-to-end speech synthesis by proposing prosody embeddings with temporal structures, enabling fine-grained control at frame and phoneme levels, and demonstrated robustness through temporal normalization against speaker perturbations.
We propose prosody embeddings for emotional and expressive speech synthesis networks. The proposed methods introduce temporal structures in the embedding networks, thus enabling fine-grained control of the speaking style of the synthesized speech. The temporal structures can be designed either on the speech side or the text side, leading to different control resolutions in time. The prosody embedding networks are plugged into end-to-end speech synthesis networks and trained without any other supervision except for the target speech for synthesizing. It is demonstrated that the prosody embedding networks learned to extract prosodic features. By adjusting the learned prosody features, we could change the pitch and amplitude of the synthesized speech both at the frame level and the phoneme level. We also introduce the temporal normalization of prosody embeddings, which shows better robustness against speaker perturbations during prosody transfer tasks.