Multidimensional Residual Learning Based on Recurrent Neural Networks for Acoustic Modeling

By Yuanyuan Zhao, Shuang Xu, Bo Xu. 2016

23 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jinyu Li
2. Dong Yu
3. Li Deng
4. Zhong Meng
5. Zhuo Chen
6. Yoshua Bengio
7. Yifan Gong
8. Zhen Huang

Citations in the corpus

• A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese (2018, neutral): “First, we can find that our best results of different modeling units are comparable or superior to the best result by the deep multidimensional residual learning with 9 LSTM layers [21], which is a hybrid LSTM-HMM system with the modeling unit of CDstates.”
• Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese (2018, neutral): “model CER LSTMP-9×800P512-F444 [24] 30.”
• Recent progresses in deep learning based acoustic models (2017, background): “Residual LSTM [30], [31] uses shortcut connections be-tween LSTM layers, and hence also provides a way to alleviating the gradient vanishing problem.”