Self-attention Based Prosodic Boundary Prediction for Chinese Speech Synthesis
By Chunhui Lu, Pengyuan Zhang, Yonghong Yan. 2019
26 citations recorded by the source corpus.
Predicting prosodic boundaries from input text plays an important role in Chinese text-to-speech (TTS) system, which directly influences the naturalness and intelligibility of synthesized speech. In this paper, we propose to combine self-attention with multitask learning for prosodic boundary prediction. Self-attention is used to capture the dependency between two arbitrary characters in the input sentence, while multitask learning models the relationships between prosodic boundaries and lexicon words by setting word segmentation as an auxiliary task. The proposed method can generate prosodic boundary labels directly from Chinese characters and achieve the whole process end-to-end. Experimental results show the effectiveness of our proposed model and prove that the performance can be further improved by pretraining the model with extra word segmentation data.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- A Survey on Neural Speech Synthesis (2021, methodology): “Some works [50, 3, 62, 322, 210, 212] investigate different model structures such as CRF [176], RNN [111], and self-attention [362] for prosody prediction in Chinese.”
- Unified Mandarin TTS Front-end Based on Distilled BERT Model (2020, methodology): “, syntactic trees based rules for PSP [3], dictionary matching et al based polyphone disambiguity [4]), or statistical learning models (like CRF [5] and LSTM/Attention based NN models [6, 7] for PSP, [8, 9] for Mandarin G2P).”
- Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “[130] also proposed a method of multitasking learning to efficiently complete PSP tasks based on the self-attention model.”