A bi-directional LSTM approach for polyphone disambiguation in Mandarin Chinese

By Changhao Shan, Lei Xie, Kaisheng Yao. 2016

27 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

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. Sheng Zhao
5. Frank K. Soong
6. Yi Ren
7. Zhou Zhao
8. Yang Zhang

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Sheng Zhao
5. Frank K. Soong
6. Yang Zhang
7. Yi Ren
8. Liqun Deng

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Thus, G2P conversion in this kind of languages is mainly responsible for polyphone disambiguation, which decides the appropriate pronunciation based on the current word context [441, 392, 224, 295, 321, 29, 257].”
• Knowledge Distillation from Bert in Pre-Training and Fine-Tuning for Polyphone Disambiguation (2019, methodology): “We compare our method with several baselines: 1) LSTM [10], which is directly trained on polyphone disambiguation dataset; 2) Transformer [14] with the same configuration with the small BERT model (3 layers and 512 hidden dims) which is also directly trained on the polyphone disambiguation dataset w”
• g2pM: A Neural Grapheme-to-Phoneme Conversion Package for MandarinChinese Based on a New Open Benchmark Dataset (2020, methodology): “Recently [1, 4] use bidirectional Long Short-Term Memory (LSTM) [11] to extract diverse features on the character, word, and sentence level.”
• Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features (2019, methodology): “The approach presented in [15] had compared with other polyphone disambiguation approaches and shown that it reaches a better performance.”
• 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).”