Self-attention Based Prosodic Boundary Prediction for Chinese Speech Synthesis
Self-attention Based Prosodic Boundary Prediction for Chinese Speech Synthesis
复制标题
DOI：
10.1109/icassp.2019.8682770
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Chunhui Lu;Pengyuan Zhang;Yonghong Yan
中科院分区：
文献类型：
--
作者：
Chunhui Lu;Pengyuan Zhang;Yonghong Yan
韵律边界预测是汉语文语转换系统中的一个重要环节，它直接影响到合成语音的自然度和可懂度。在本文中，我们提出了联合收割机自我注意与多任务学习的韵律边界预测。自我注意用于捕获输入句子中两个任意字符之间的依赖关系，而多任务学习通过设置分词作为辅助任务来建模韵律边界和词典单词之间的关系。该方法可以直接从汉字中生成韵律边界标签，并实现了整个过程的端到端。实验结果表明，我们提出的模型的有效性，并证明了性能可以进一步提高预训练模型与额外的分词数据。
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.