Locating Boundaries for Prosodic Constituents in Unrestricted Mandarin Texts

By Min Chu, Yao Qian. 2001

74 citations recorded by the source corpus.

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

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Xinyu Yang
6. Zhaoxi Mu
7. Yizhuo Dong
8. Sheng Zhao

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “For Chinese speech synthesis, the typical prosody boundary labels consist of prosodic word (PW), prosodic phrase (PPH) and intonational phrase (IPH), which can construct a three-layer hierarchical prosody tree [50, 322, 62].”
• Automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features (2015, background): “Index Terms— automatic prosody prediction, speech synthesis, neural network, BLSTM, embedding features”
• Self-attention Based Prosodic Boundary Prediction for Chinese Speech Synthesis (2019, background): “In Chinese text-to-speech (TTS) systems, a hierarchical prosodic structure, including prosodic word (PW), prosodic phrase (PPH) and intonational phrase (IPH), is widely employed to distinguish different levels of pauses between words [1].”
• A Mandarin Prosodic Boundary Prediction Model Based on Multi-Task Learning (2019, background): “In brief, previous studies on mandarin prosodic boundary prediction mainly focused on two main aspects: 1) studying the impact of different kinds of features [1,2,4]; 2) exploring suitable models and architectures [3-4].”
• Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “Taking Mandarin as an example, the prosodic structure of Mandarin is a three-level hierarchical structure composed of three basic units: prosodic words (PW), prosodic phrases (PPH) and intonation phrases (IPH) [35].”
• Chinese Prosody Structure Prediction Based on Conditional Random Fields (2009, methodology): “The CART-based modeling, which is the classical prosody structure prediction method, is applied as a comparison with the same corpus and features used.”