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

arXiv: https://arxiv.org/abs/2203.16922 · HTML: https://mlsanity.com/paper/2203.16922/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [A Minimal Span-Based Neural Constituency Parser](https://mlsanity.com/paper/1705.03919/) (2017)
- [What's Going On in Neural Constituency Parsers? An Analysis](https://mlsanity.com/paper/1804.07853/) (2018)
- [Unified Mandarin TTS Front-end Based on Distilled BERT Model](https://mlsanity.com/paper/2012.15404/) (2020)
- [Automatic Prosody Prediction for Chinese Speech Synthesis using BLSTM-RNN and Embedding Features](https://mlsanity.com/paper/1511.00360/) (2015)

## Built on by (most cited first, 4 of 4)

- [StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis](https://mlsanity.com/paper/2312.12181/) (2023)
- [CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction](https://mlsanity.com/paper/2406.08336/) (2024)
- [Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP](https://mlsanity.com/paper/2309.05423/) (2023)
- [Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model](https://mlsanity.com/paper/2309.11000/) (2023)

## Abstract (arXiv)

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.