arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.16922cs.CLcs.SDeess.AS
收藏

基于跨度的汉语韵律结构预测模型

A Character-level Span-based Model for Mandarin Prosodic Structure Prediction

Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems(清华-港中文媒体科学、技术与系统联合研究中心);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);The Chinese University of Hong Kong(香港中文大学);TAL Education Group(好未来教育集团)

Xueyuan Chen, Changhe Song, Yixuan Zhou, Zhiyong Wu, Changbin Chen, Zhongqin Wu, Helen Meng

摘要:

韵律结构预测的准确性对汉语文语转换系统中合成语音的自然度至关重要,但目前普遍采用的序列到序列框架和以往分词结果的误差积累限制了韵律结构预测的准确性。本文提出了一种基于跨度的汉语韵律结构预测模型,以获得最优的韵律结构树,并将其转换为相应的韵律标签序列。该方法不需要分词的前提条件,而是由汉字级BERT提供丰富的语言特征,并将其发送给具有自注意结构的编码器。在此基础上,使用跨度表示和标签评分来描述所有可能的韵律结构树,其中每棵树都有其对应的分数。为了找到给定句子的最佳树,进一步使用自底向上的CKY风格算法。该方法可以同时预测不同层次的韵律标签,并以端到端的方式直接从汉字中完成这一过程。两个真实世界的数据集上的实验结果表明,我们的基于跨度的方法在所有序列到序列的基线方法的优异性能。

英文摘要:

The accuracy of prosodic structure prediction is crucial to the naturalness of synthesized speech in Mandarin text-to-speech system, but now is limited by widely-used sequence-to-sequence framework and error accumulation from previous word segmentation results. In this paper, we propose a span-based Mandarin prosodic structure prediction model to obtain an optimal prosodic structure tree, which can be converted to corresponding prosodic label sequence. Instead of the prerequisite for word segmentation, rich linguistic features are provided by Chinese character-level BERT and sent to encoder with self-attention architecture. On top of this, span representation and label scoring are used to describe all possible prosodic structure trees, of which each tree has its corresponding score. To find the optimal tree with the highest score for a given sentence, a bottom-up CKY-style algorithm is further used. The proposed method can predict prosodic labels of different levels at the same time and accomplish the process directly from Chinese characters in an end-to-end manner. Experiment results on two real-world datasets demonstrate the excellent performance of our span-based method over all sequence-to-sequence baseline approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑