Publications
CONFERENCE (INTERNATIONAL) DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning
Takaaki Saeki (The University of Tokyo), Kentaro Tachibana, Ryuichi Yamamoto
The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022)
September 18, 2022
Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech corpora as training data. However, they only address either time-invariant or time-variant noises. We propose a degradation-robust TTS method, which can be trained on speech corpora that contain both additive noises and environmental distortions. It jointly represents the time-variant additive noises with a frame-level encoder and the time-invariant environmental distortions with an utterance-level encoder. We also propose a regularization method to attain clean environmental embedding that is disentangled from the utterance-dependent information such as linguistic contents and speaker characteristics. Evaluation results show that our method achieved significantly higher-quality synthetic speech than previous methods in the condition including both additive noise and reverberation.
Paper :
DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning
(external link)