Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information
This work addresses the problem of producing more natural and intelligible speech in Mandarin TTS systems, representing an incremental improvement by extending existing methods to include contextual information.
The paper tackled prosodic structure prediction for Mandarin text-to-speech by incorporating inter-utterance linguistic information, achieving better F1 scores for prosodic word, phrase, and intonational phrase predictions on two datasets and improving speech naturalness in subjective tests.
For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic information can influence the speech interpretation of the target utterance, previous works on PSP mainly focus on utilizing intrautterance linguistic information of the current utterance only. This work proposes to use inter-utterance linguistic information to improve the performance of PSP. Multi-level contextual information, which includes both inter-utterance and intrautterance linguistic information, is extracted by a hierarchical encoder from character level, utterance level and discourse level of the input text. Then a multi-task learning (MTL) decoder predicts prosodic boundaries from multi-level contextual information. Objective evaluation results on two datasets show that our method achieves better F1 scores in predicting prosodic word (PW), prosodic phrase (PPH) and intonational phrase (IPH). It demonstrates the effectiveness of using multi-level contextual information for PSP. Subjective preference tests also indicate the naturalness of synthesized speeches are improved.