Expressive TTS Training with Frame and Style Reconstruction Loss
This work addresses the problem of generating more expressive speech for TTS applications, representing an incremental but notable advancement in prosody modeling without explicit annotations.
The paper tackles the challenge of improving expressiveness in text-to-speech systems without requiring prosody annotations, by proposing a novel training strategy that combines frame-level and utterance-level style reconstruction losses. The method outperforms a state-of-the-art baseline in naturalness and expressiveness, marking the first incorporation of utterance-level perceptual quality as a loss function in Tacotron training.
We propose a novel training strategy for Tacotron-based text-to-speech (TTS) system to improve the expressiveness of speech. One of the key challenges in prosody modeling is the lack of reference that makes explicit modeling difficult. The proposed technique doesn't require prosody annotations from training data. It doesn't attempt to model prosody explicitly either, but rather encodes the association between input text and its prosody styles using a Tacotron-based TTS framework. Our proposed idea marks a departure from the style token paradigm where prosody is explicitly modeled by a bank of prosody embeddings. The proposed training strategy adopts a combination of two objective functions: 1) frame level reconstruction loss, that is calculated between the synthesized and target spectral features; 2) utterance level style reconstruction loss, that is calculated between the deep style features of synthesized and target speech. The proposed style reconstruction loss is formulated as a perceptual loss to ensure that utterance level speech style is taken into consideration during training. Experiments show that the proposed training strategy achieves remarkable performance and outperforms a state-of-the-art baseline in both naturalness and expressiveness. To our best knowledge, this is the first study to incorporate utterance level perceptual quality as a loss function into Tacotron training for improved expressiveness.