A unified front-end framework for English text-to-speech synthesis
This addresses the issue of interdependent module neglect in English TTS systems, offering a unified solution for improved synthesis quality.
The paper tackles the problem of sub-optimal performance in English text-to-speech front-end modules by proposing a unified framework that captures dependencies among them, achieving state-of-the-art performance in all modules.
The front-end is a critical component of English text-to-speech (TTS) systems, responsible for extracting linguistic features that are essential for a text-to-speech model to synthesize speech, such as prosodies and phonemes. The English TTS front-end typically consists of a text normalization (TN) module, a prosody word prosody phrase (PWPP) module, and a grapheme-to-phoneme (G2P) module. However, current research on the English TTS front-end focuses solely on individual modules, neglecting the interdependence between them and resulting in sub-optimal performance for each module. Therefore, this paper proposes a unified front-end framework that captures the dependencies among the English TTS front-end modules. Extensive experiments have demonstrated that the proposed method achieves state-of-the-art (SOTA) performance in all modules.