A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognition
By Xuerui Yang, Jiwei Li, Xi Zhou. 2018
15 citations recorded by the source corpus.
Deep Feedforward Sequential Memory Network (DFSMN) has shown superior performance on speech recognition tasks. Based on this work, we propose a novel network architecture which introduces pyramidal memory structure to represent various context information in different layers. Additionally, res-CNN layers are added in the front to extract more sophisticated features as well. Together with lattice-free maximum mutual information (LF-MMI) and cross entropy (CE) joint training criteria, experimental results show that this approach achieves word error rates (WERs) of 3.62% and 10.89% respectively on Librispeech and LDC97S62 (Switchboard 300 hours) corpora. Furthermore, Recurrent neural network language model (RNNLM) rescoring is applied and a WER of 2.97% is obtained on Librispeech.
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
In Signal Processing
Citations in the corpus
- State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention with Dilated 1D Convolutions (2019, methodology): “The hybrid DNN/HMM approach was used for the different neural network acoustic models of CNN-biLSTM, pyramidal Feedforward Sequential Memory Network (FSMN), and BiL-STM, respectively, in [35, 36, 37].”