Year: 2020
Type: article
Abstract: We introduce a novel speech synthesis system, called NAUTILUS, that can generate speech with a target voice either from a text input or a reference utterance of an arbitrary source speaker. By using a multi-speaker speech corpus to train all requisite encoders and decoders in the initial training stage, our system can clone unseen voices using untranscribed speech of target speakers on the basis of the backpropagation algorithm. Moreover, depending on the data circumstance of the target speaker, the cloning strategy can be adjusted to take advantage of additional data and modify the behaviors of text-to-speech (TTS) and/or voice conversion (VC) systems to accommodate the situation. We test the performance of the proposed framework by using deep convolution layers to model the encoders, decoders and WaveNet vocoder. Evaluations show that it achieves comparable quality with state-of-the-art TTS and VC systems when cloning with just five minutes of untranscribed speech. Moreover, it is demonstrated that the proposed framework has the ability to switch between TTS and VC with high speaker consistency, which will be useful for many applications.
Authors: Hieu-Thi Luong, Junichi Yamagishi
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,045
Awards: G1526460031, G1710514051, Biometric Information Protection Utilization Infrastructure to Ensure Personal Convenience and Prevent Identity Theft, G4104777191, G5216536157, G5375717198, PRISM: Speech privacy preservation based on selecting masking, G6718509927, Communication System for Defending against Attacks of Media Clones, Robust voice cloning technologies in noisy environments and its applications, G7879866177, G8315410620, Safe and secure speech information processing based on liveness detection and ASVspoof challenge
OpenAlex ID: W3095990227
